Google Hummingbird Algorithm Update: A Move to Conversational Search
| Tuesday, November 12, 2013
A hummingbird is a very amazing creature. Did you know that hummingbirds are the smallest of the bird family yet they are amazingly fast and quick? In some cases their wings can reach 100 beats per second. That’s pretty quick for such a little bird. So when Google decides to make a major algorithm change, what do they use for a code name? Hummingbird of course… The name was most likely associated with the fact that Google is looking to help users find their information quicker when they perform a search on Google. What’s all the fuss about hummingbirds?
Well in August 2013, Google launched their largest algorithm update in years with their Google Hummingbird algorithm update.
What is Google Hummingbird?
Google Hummingbird, officially announced
on September 26th
, 2013, is basically a rewriting of Google’s Algorithm and focuses on Google’s interpretation of the answer that a user is looking for when they perform a query. The predecessor to Hummingbird was Google Caffeine
in 2009/2010 which was more of an attempt to better crawl and index content.
With the Hummingbird algorithm update, Google is more focused on “ranking” sites better for relevance. Hummingbird is more about Google’s interpretation of the answer that a user is looking for when they perform a query. This interpretation is based on the information Google has around that query, personalized search activity, and search history.
Think of Hummingbird as Google moving away from trying to interpret “typed searches” to better understanding searches that are more colloquial or conversational in nature.Google states that Hummingbird is about better understanding concepts vs. words and the relationships of those concepts.
Hummingbird is about Google trying to produce a more intelligent search engine.
According to Google, each word in a query will receive attention with Hummingbird. This falls in line with data presented in recent years suggesting that the largest increase in search queries is for more complex, 8 or more word queries. (Read: People are becoming more savvy searchers or have a lot of questions). So it stands to reason that with increasingly complicated searches, Google’s results should be more relevant to the user’s query right? A smarter search engine is required.
Google is stating that the Hummingbird algorithm is much more intelligent than previous algorithms. It is able to answer questions, filter the answers and even present comparison data with but a glance. The algorithm is meant to provide the searcher with highly relevant results quicker than before.
In fact, Google is suggesting that you may not even have to leave their SERP because you will be able to find the answer that you are looking for via Knowledge Graph, carousel results or via the web pages that are served up
. The data will be right there for the taking… or consuming in this case. This algorithm is more focused on semantics as opposed to the traditional robot-like “typed” queries that people search for. Google is using information from their database to anticipate the answer to your query. Part of the purpose for Hummingbird is to improve results for more complicated or conversational searches. There is a dramatic push for their Knowledge Graph
results. Ultimately what Google is saying is that they want to provide the most relevant results as quickly as possible.
Google’s Hummingbird update is very different than the recent Panda and Penguin updates. Those algorithm updates were based on the existing algorithms and focused on things like low quality content, over-optimization and link spam. The Hummingbird update is a larger more powerful update that dramatically alters how Google returns the results that they do from their index.
According to Google, the Hummingbird update affected 90% of searches worldwide.
Two Main Changes with Google Hummingbird
- Move to semantic/conversational search results – instead of traditional keyword searches, Hummingbird uses conversational searches to deliver search results that are more on point with what users are looking for.
- More Focus on Complex Queries / Mobile search – with more and more people using mobile phones and mobile search, Google is attempting to better understand and anticipate the answers to what people are seeking on their mobile devices. According to Google’s SVP of Search Amit Singhal, “Google will keep reinventing itself to give you all you need for a simple and intuitive experience. At some point, pulling out a smartphone to do a search will feel as archaic as a dial-up modem.” Android anyone?
What Does this Mean for my Keyword Strategy?
You are probably wondering what this means for the keywords that you are focusing on? Well the days of optimizing a given web page for a given key phrase and having that page rank as a result are long gone. Of course keywords will always be a key component of the activity of searching. In fact I referred to the shift towards semantic search as part of keyword research in my piece on the future of keyword research
in organic search earlier this year.
Areas that you need to consider as a result of Hummingbird:
- The need for keyword analysis and keyword research has never been more important.
- Pay attention to what your audience is searching for.
- Avoid using marketing jargon in your messaging. The messaging on your site needs to be clear, concise and relevant to your audience.
- Do not keyword stuff content but be aware of the semantic relationships of topics and phrases that you are optimizing for.
As an example, if your site sells “digital cameras” you are not solely going to “optimize” for just digital cameras. Your audience may be looking for information on: various brands, manufacturers, parts of the camera, accessories, photography, battery packs, memory cards, imagery, etc.
Be tuned into your target audience and what they are truly searching for.
You should be learning more about semantic search and about understanding the relationships, concepts and questions that your audience is seeking answers to. Understand the shift from “typed” keyword queries to more complicated semantic, conversational search.
At the end of the day, Hummingbird is focused (in part) on Natural Language Processing. Therefore the need to pay attention to hyper long-tail keyword queries or questions becomes tremendously important. Some have even gone so far to refer to this as evaluating the long-tail of the long-tail.
Google’s Amit Singhal was quoted as stating, “With more complex queries, the algorithm can better understand concepts vs. words as well as relationships between concepts.” It is no longer just about the keyword, it is more about the relationship of keywords and about the concept or question that a user may seek information about.
What is the Impact on My Content Strategy?
If you have not yet figured it out, content is the key to your success, especially from an organic search perspective. Hummingbird will have an impact on how you produce, optimize and promote your content.
Here are five areas to revisit as you establish your content strategies.
- Enhance existing content – revisit your existing content. Do you feel that it is of high quality? Does it satisfy the needs of someone looking for information about your brand or your solution offering? Is the content unique? Is the content engaging? Expand your existing content as required to help you address questions that your audience may have.
- Improve the level of detail in your product/solution descriptions, articles or blog posts – build themes and interlink relevant content where you have optimized for similar terms and topics. Be concise yet have enough detail that will allow the searcher to obtain the answer to their query.
- FAQs are important – providing detailed answers to frequently asked questions goes a long way. Work on being an authority. Provide the answers to the questions that your audience is looking for. Do not spam your FAQs with regurgatated content. Produce unique, fresh and informative content.
- Leverage Rich markup with your content – incorporate schema.org markup, authorship markup and rich markup in your content. Semantic markup is what Google and other search engines are moving towards. The use of schema or microdata can help the search engines better understand what is being discussed on your pages. Not familiar with schema? Why not get started now?
- Optimize for Mobile – again part of the Hummingbird update is Google trying to get better at parsing voice commands and questions from mobile devices. Optimizing your site for mobile search is critical to address this. Responsive design anyone?
Google Hummingbird is forming the foundation of the next wave of semantic search… the impact of which may take months or even years for the full effect to take place.
|posted by Jody @ 7:39 PM
Making Flow Happen: Dashboards that Persuade, Inform, and Engage
| Tuesday, October 29, 2013
Labels: analytics, dashboard reporting, dashboards, Tableau
|posted by Jody @ 9:38 AM
Link Building in 2013-2014
| Wednesday, May 22, 2013
|posted by Jody @ 10:45 AM
Google Penguin 2.0: What Will It Mean for You?
| Tuesday, May 14, 2013
Labels: algorithim update, google penguin, Penguin 2.0
|posted by Jody @ 3:49 PM
Definitive List of Google Updates 2012
| Wednesday, October 17, 2012
||Google admits to making hundreds of algorithm updates every year. They are not joking when they state this. Google tweak their algorithms will regular occurence. In the first three quarters of 2012, Google has made a number of algorithm updates (300+ actually). We've outlined some of the major ones below.
Google Algo Updates for 2012
Google started the year rolling out these updates:
- Image Search landing page quality signals. [launch codename “simple”] This is an improvement that analyzes various landing page signals for Image Search. We want to make sure that not only are we showing you the most relevant images, but we are also linking to the highest quality source pages.
- More relevant sitelinks. [launch codename “concepts”, project codename “Megasitelinks”] We improved our algorithm for picking sitelinks. The result is more relevant sitelinks; for example, we may show sitelinks specific to your metropolitan region, which you can control with your location setting.
- Soft 404 Detection. Web servers generally return the 404 status code when someone requests a page that doesn’t exist. However, some sites are configured to return other status codes, even though the page content might explain that the page was not found. We call these soft 404s (or “crypto” 404s) and they can be problematic for search engines because we aren’t sure if we should ignore the pages. This change is an improvement to how we detect soft 404s, especially in Russian, German and Spanish. For all you webmasters out there, the best practice is still to always use the correct response code.
- More accurate country-restricted searches. [launch codename “greencr”] On domains other than .com, users have the option to see only results from their particular country. This is a new algorithm that uses several signals to better determine where web documents are from, improving the accuracy of this feature.
- More rich snippets. We improved our process for detecting sites that qualify for shopping, recipe and review rich snippets. As a result, you should start seeing more sites with rich snippets in search results.
- Better infrastructure for autocomplete. This is an infrastructure change to improve how our autocomplete algorithm handles spelling corrections for query prefixes (the beginning part of a search).
- Better spam detection in Image Search. [launch codename “leaf”] This change improves our spam detection in Image Search by extending algorithms we already use for our main search results.
- Google Instant enhancements for Japanese. For languages that use non-Latin characters, many users use a special IME (Input Method Editor) to enter queries. This change works with browsers that are IME-aware to better handle Japanese queries in Google Instant.
- More accurate byline dates. [launch codename “foby”] We made a few improvements to how we determine what date to associate with a document. As a result, you’ll see more accurate dates annotating search results.
- Live results for NFL and college football. [project codename “Live Results”] We’ve added new live results for NFL.com and ESPN’s NCAA Football results. These results now provide the latest scores, schedules and standings for your favorite football teams.
- Improved dataset for related queries. We are now using an improved dataset on term relationships to find related queries. We sometimes include results for queries that are related to your original search, and this improvement leads to results from more relevant related queries.
- Related query improvements. [launch codename “lyndsy”] Sometimes we fetch results for queries that are related to the original query but have fewer words. We made several changes to our algorithms to make them more conservative and less likely to introduce results without query words.
- Better lyrics results. [launch codename “baschi”, project codename “Contra”] This change improves our result quality for lyrics searches.
- Tweak to +1 button on results page. As part of our continued effort to deliver a beautifully simple user experience across Google products, we’ve made a subtle tweak to how the +1 button appears on the results page. Now the +1 button will only appear when you hover over a result or when the result has already been +1’d.
- Better spell correction in Vietnamese. [project codename “Pho Viet”] We launched a new Vietnamese spelling model. This will help give more accurate spelling predictions for Vietnamese queries.
- Upcoming events at venues. We've improved the recently released places panel for event venues. For major venues, we now show up to three upcoming events on the right of the page. Try it for [staples center los angeles] or [paradise rock club boston].
- Improvements to image size signal. [launch codename “matter”] This is an improvement to how we use the size of images as a ranking signal in Image Search. With this change, you’ll tend to see images with larger full-size versions.
- Improved Hebrew synonyms. [launch codename “SweatNovember”, project codename “Synonyms”] This update refines how we handle Hebrew synonyms across multiple languages. Context matters a lot for translation, so this change prevents us from using translated synonyms that are not actually relevant to the query context.
- Safer searching. [launch codename “Hoengg”, project codename "SafeSearch"] We updated our SafeSearch tool to provide better filtering for certain queries when strict SafeSearch is enabled.
- Encrypted search available on new regional domains. Google now offers encrypted search by default on google.com for signed-in users, but it’s not the default on our other regional domains (eg: google.fr for France). Now users in the UK, Germany and France can opt in to encrypted search by navigating directly to an SSL version of Google Search on their respective regional domains: https://www.google.co.uk, https://www.google.de and https://www.google.fr.
- Faster mobile browsing. [launch codename “old possum”, project codename “Skip Redirect”] Many websites redirect smartphone users to another page that is optimized for smartphone browsers. This change uses the final smartphone destination url in our mobile search results, so you can bypass all the redirects and load the target page faster.
- Search + Your World - January 10, 2012 - Google announced a radical shift in personalization - aggressively pushing Google+ social data and user profiles into SERPs with their Search + Your World announcement. Google also added a new, prominent toggle button to shut off personalization.
- Panda 3.2 - January 18, 2012 - Google confirmed a Panda data update, although suggested that the algorithm hadn't changed.
- Too Many Ads Above The Fold - January 19, 2012 - Google updated their page layout algorithms to devalue sites with too much ad-space above the "fold". It had been suspected that a similar factor was in play in Panda. In fact we did see this with some sites with the initial Panda algorithm update.
- Fresher results. [launch codename “nftc”] We made several adjustments to the freshness algorithm that we released in November. These are minor updates to make sure we continue to give you the freshest, most relevant results.
- Faster autocomplete. [launch codename “Snappy Suggest”, project codename “Suggest”] We made improvements to our autocomplete system to deliver your predicted queries much faster.
- Autocomplete spelling corrections. [launch codename “Trivial”, project codename “Suggest”] This is an improvement to the spelling corrections used in autocomplete, making those corrections more consistent with the spelling corrections used in search. This launch targets corrections where the spelling change is very small.
- Better spelling full-page replacement. [launch codenames “Oooni”, “sgap”, project codename “Full-Page Replacement”] When we’re confident in a spelling correction we automatically show results for the corrected query and let you know we’re “Showing results for [cheetah]” (rather than, say, “cheettah”). We made a couple of changes to improve the accuracy of this feature.
- Better spelling corrections for rare queries. This change improves one of the models that we use to make spelling corrections. The result is more accurate spell corrections for a number of rare queries.
- Improve detection of recurrent event pages. [launch codename “neseda”] We made several improvements to how we determine the date of a document. As a result, you’ll see fresher, more timely results, particularly for pages discussing recurring events.
- High-quality sites algorithm improvements. [launch codenames “PPtl” and “Stitch”, project codename “Panda”] In 2011, we launched the Panda algorithm change, targeted at finding more high-quality sites. We improved how Panda interacts with our indexing and ranking systems, making it more integrated into our pipelines. We also released a minor update to refresh the data for Panda.
- Cross-language refinements. [launch codename Xiangfan] Previously, we only generated related searches based on the display language. With this change, we also attempt to auto-detect the language of the original query to generate related search queries. Now, a user typing a query in French might see French query refinements, even if her language is set to English.
- English on Google Saudi Arabia. Users in Saudi Arabia can now more easily choose an English interface to search on google.com.sa.
- Improved scrolling for Image Search. Previously when you scrolled in Image Search, only the image results would move while the top and side menus were pinned in place. We changed the scrolling behavior to make it consistent with our main search results and the other search modes, where scrolling moves the entire page.
- Improved image search quality. [launch codename “endearo”, project codename “Image Search”] This is a small improvement to our image search ranking algorithm. In particular, this change helps images with high-quality landing pages rank higher in our image search results.
- More relevant related searches. Sometimes at the bottom of the screen you’ll see a section called “Searches related to” with other queries you may want to try. With this change, we’ve updated the model for generating related searches, resulting in more useful query refinements.
- Blending of news results. [launch codename “final-destination”, project codename “Universal Search”] We improved our algorithm that decides which queries should show news results, making it more responsive to realtime trends. We also made an adjustment to how we blend news results in Universal Search. Both of these changes help news articles appear in your search results when they are relevant.
- Automatically disable Google Instant based on computer speed. [project codename “Psychic Search”] Google Instant has long had the ability to automatically turn itself off if you’re on a slow internet connection. Now Instant can also turn itself off if your computer is slow. If Instant gets automatically disabled, we continue to check your computer speed and will re-enable Instant if your performance improves. We’ve also tweaked search preferences so you can always have Instant on or off, or have it change automatically.
- Venice Update - February 27, 2012? - As part of their monthly updates, Google mentioned an update code-name "Venice". This local update appeared to more aggressively localize organic results and more tightly integrate local search data.
- More coverage for related searches. [launch codename “Fuzhou”] This launch brings in a new data source to help generate the “Searches related to” section, increasing coverage significantly so the feature will appear for more queries. This section contains search queries that can help you refine what you’re searching for.
- Tweak to categorizer for expanded sitelinks. [launch codename “Snippy”, project codename “Megasitelinks”] This improvement adjusts a signal we use to try and identify duplicate snippets. We were applying a categorizer that wasn’t performing well for our expanded sitelinks, so we’ve stopped applying the categorizer in those cases. The result is more relevant sitelinks.
- Less duplication in expanded sitelinks. [launch codename “thanksgiving”, project codename “Megasitelinks”] We’ve adjusted signals to reduce duplication in the snippets for expanded sitelinks. Now we generate relevant snippets based more on the page content and less on the query.
- More consistent thumbnail sizes on results page. We’ve adjusted the thumbnail size for most image content appearing on the results page, providing a more consistent experience across result types, and also across mobile and tablet. The new sizes apply to rich snippet results for recipes and applications, movie posters, shopping results, book results, news results and more.
- More locally relevant predictions in YouTube. [project codename “Suggest”] We’ve improved the ranking for predictions in YouTube to provide more locally relevant queries. For example, for the query [lady gaga in ] performed on the US version of YouTube, we might predict [lady gaga in times square], but for the same search performed on the Indian version of YouTube, we might predict [lady gaga in India].
- More accurate detection of official pages. [launch codename “WRE”] We’ve made an adjustment to how we detect official pages to make more accurate identifications. The result is that many pages that were previously misidentified as official will no longer be.
- Refreshed per-URL country information. [Launch codename “longdew”, project codename “country-id data refresh”] We updated the country associations for URLs to use more recent data.
- Expand the size of our images index in Universal Search. [launch codename “terra”, project codename “Images Universal”] We launched a change to expand the corpus of results for which we show images in Universal Search. This is especially helpful to give more relevant images on a larger set of searches.
- Minor tuning of autocomplete policy algorithms. [project codename “Suggest”] We have a narrow set of policies for autocomplete for offensive and inappropriate terms. This improvement continues to refine the algorithms we use to implement these policies.
- “Site:” query update [launch codename “Semicolon”, project codename “Dice”] This change improves the ranking for queries using the “site:” operator by increasing the diversity of results.
- Improved detection for SafeSearch in Image Search. [launch codename "Michandro", project codename “SafeSearch”] This change improves our signals for detecting adult content in Image Search, aligning the signals more closely with the signals we use for our other search results.
- Interval based history tracking for indexing. [project codename “Intervals”] This improvement changes the signals we use in document tracking algorithms.
- Improvements to foreign language synonyms. [launch codename “floating context synonyms”, project codename “Synonyms”] This change applies an improvement we previously launched for English to all other languages. The net impact is that you’ll more often find relevant pages that include synonyms for your query terms.
- Disabling two old fresh query classifiers. [launch codename “Mango”, project codename “Freshness”] As search evolves and new signals and classifiers are applied to rank search results, sometimes old algorithms get outdated. This improvement disables two old classifiers related to query freshness.
- More organized search results for Google Korea. [launch codename “smoothieking”, project codename “Sokoban4”] This significant improvement to search in Korea better organizes the search results into sections for news, blogs and homepages.
- Fresher images. [launch codename “tumeric”] We’ve adjusted our signals for surfacing fresh images. Now we can more often surface fresh images when they appear on the web.
- Update to the Google bar. [project codename “Kennedy”] We continue to iterate in our efforts to deliver a beautifully simple experience across Google products, and as part of that this month we made further adjustments to the Google bar. The biggest change is that we’ve replaced the drop-down Google menu in the November redesign with a consistent and expanded set of links running across the top of the page.
- Adding three new languages to classifier related to error pages. [launch codename "PNI", project codename "Soft404"] We have signals designed to detect crypto 404 pages (also known as “soft 404s”), pages that return valid text to a browser but the text only contain error messages, such as “Page not found.” It’s rare that a user will be looking for such a page, so it’s important we be able to detect them. This change extends a particular classifier to Portuguese, Dutch and Italian.
- Improvements to travel-related searches. [launch codename “nesehorn”] We’ve made improvements to triggering for a variety of flight-related search queries. These changes improve the user experience for our Flight Search feature with users getting more accurate flight results.
- Data refresh for related searches signal. [launch codename “Chicago”, project codename “Related Search”] One of the many signals we look at to generate the “Searches related to” section is the queries users type in succession. If users very often search for [apple] right after [banana], that’s a sign the two might be related. This update refreshes the model we use to generate these refinements, leading to more relevant queries to try.
- International launch of shopping rich snippets. [project codename “rich snippets”] Shopping rich snippets help you more quickly identify which sites are likely to have the most relevant product for your needs, highlighting product prices, availability, ratings and review counts. This month we expanded shopping rich snippets globally (they were previously only available in the US, Japan and Germany).
- Improvements to Korean spelling. This launch improves spelling corrections when the user performs a Korean query in the wrong keyboard mode (also known as an "IME", or input method editor). Specifically, this change helps users who mistakenly enter Hangul queries in Latin mode or vice-versa.
- Improvements to freshness. [launch codename “iotfreshweb”, project codename “Freshness”] We’ve applied new signals which help us surface fresh content in our results even more quickly than before.
- Web History in 20 new countries. With Web History, you can browse and search over your search history and webpages you've visited. You will also get personalized search results that are more relevant to you, based on what you’ve searched for and which sites you’ve visited in the past. In order to deliver more relevant and personalized search results, we’ve launched Web History in Malaysia, Pakistan, Philippines, Morocco, Belarus, Kazakhstan, Estonia, Kuwait, Iraq, Sri Lanka, Tunisia, Nigeria, Lebanon, Luxembourg, Bosnia and Herzegowina, Azerbaijan, Jamaica, Trinidad and Tobago, Republic of Moldova, and Ghana. Web History is turned on only for people who have a Google Account and previously enabled Web History.
- Improved snippets for video channels. Some search results are links to channels with many different videos, whether on mtv.com, Hulu or YouTube. We’ve had a feature for a while now that displays snippets for these results including direct links to the videos in the channel, and this improvement increases quality and expands coverage of these rich “decorated” snippets. We’ve also made some improvements to our backends used to generate the snippets.
- Improvements to ranking for local search results. [launch codename “Venice”] This improvement improves the triggering of Local Universal results by relying more on the ranking of our main search results as a signal.
- Improvements to English spell correction. [launch codename “Kamehameha”] This change improves spelling correction quality in English, especially for rare queries, by making one of our scoring functions more accurate.
- Improvements to coverage of News Universal. [launch codename “final destination”] We’ve fixed a bug that caused News Universal results not to appear in cases when our testing indicates they’d be very useful.
- Consolidation of signals for spiking topics. [launch codename “news deserving score”, project codename “Freshness”] We use a number of signals to detect when a new topic is spiking in popularity. This change consolidates some of the signals so we can rely on signals we can compute in realtime, rather than signals that need to be processed offline. This eliminates redundancy in our systems and helps to ensure we can continue to detect spiking topics as quickly as possible.
- Better triggering for Turkish weather search feature. [launch codename “hava”] We’ve tuned the signals we use to decide when to present Turkish users with the weather search feature. The result is that we’re able to provide our users with the weather forecast right on the results page with more frequency and accuracy.
- Visual refresh to account settings page. We completed a visual refresh of the account settings page, making the page more consistent with the rest of our constantly evolving design.
- Panda update. This launch refreshes data in the Panda system, making it more accurate and more sensitive to recent changes on the web.
- Link evaluation. We often use characteristics of links to help us figure out the topic of a linked page. We have changed the way in which we evaluate links; in particular, we are turning off a method of link analysis that we used for several years. We often rearchitect or turn off parts of our scoring in order to keep our system maintainable, clean and understandable.
- SafeSearch update. We have updated how we deal with adult content, making it more accurate and robust. Now, irrelevant adult content is less likely to show up for many queries.
- Spam update. In the process of investigating some potential spam, we found and fixed some weaknesses in our spam protections.
- Improved local results. We launched a new system to find results from a user’s city more reliably. Now we’re better able to detect when both queries and documents are local to the user.
- Panda 3.3 - February 27, 2012 - Google rolled out another Panda update, which appeared to be relatively minor. This came just 3 days after the 1-year anniversary of Panda, an unprecedented lifespan for a named update.
- Panda 3.4 - March 23, 2012 - Google announced another Panda update, this time via Twitter as the update was rolling out. It was estimated that Panda 3.4 impacted about 1.6% of search results.
- Autocomplete with math symbols. [launch codename "Blackboard", project codename "Suggest"] When we process queries to return predictions in autocomplete, we generally normalize them to match more relevant predictions in our database. This change incorporates several characters that were previously normalized: “+”, “-”, “*”, “/”, “^”, “(“, “)”, and “=”. This should make it easier to search for popular equations, for example [e = mc2] or [y = mx+b].
- Improvements to handling of symbols for indexing. [launch codename "Deep Maroon"] We generally ignore punctuation symbols in queries. Based on analysis of our query stream, we’ve now started to index the following heavily used symbols: “%”, “$”, “\”, “.”, “@”, “#”, and “+”. We’ll continue to index more symbols as usage warrants.
- Better scoring of news groupings. [launch codename "avenger_2"] News results on Google are organized into groups that are about the same story. We have scoring systems to determine the ordering of these groups for a given query. This subtle change slightly improves our scoring system, leading to better ranking of news clusters.
- Sitelinks data refresh. [launch codename "Saralee-76"] Sitelinks (the links that appear beneath some search results and link deeper into the respective site) are generated in part by an offline process that analyzes site structure and other data to determine the most relevant links to show users. We’ve recently updated the data through our offline process. These updates happen frequently (on the order of weeks).
- Improvements to autocomplete backends, coverage. [launch codename "sovereign", project codename "Suggest"] We’ve consolidated systems and reduced the number of backend calls required to prepare autocomplete predictions for your query. The result is more efficient CPU usage and more comprehensive predictions.
- Better handling of password changes. Our general approach is that when you change passwords, you’ll be signed out from your account on all machines. This change ensures that changing your password more consistently signs your account out of Search, everywhere.
- Better indexing of profile pages. [launch codename "Prof-2"] This change improves the comprehensiveness of public profile pages in our index from more than two-hundred social sites.
- UI refresh for News Universal. [launch codename "Cosmos Newsy", project codename "Cosmos"] We’ve refreshed the design of News Universal results by providing more results from the top cluster, unifying the UI treatment of clusters of different sizes, adding a larger font for the top article, adding larger images (from licensed sources), and adding author information.
- Improvements to results for navigational queries. [launch codename "IceMan5"] A “navigational query” is a search where it looks like the user is looking to navigate to a particular website, such as [New York Times] or [wikipedia.org]. While these searches may seem straightforward, there are still challenges to serving the best results. For example, what if the user doesn’t actually know the right URL? What if the URL they’re searching for seems to be a parked domain (with no content)? This change improves results for this kind of search.
- High-quality sites algorithm data update and freshness improvements. [launch codename “mm”, project codename "Panda"] Like many of the changes we make, aspects of our high-quality sites algorithm depend on processing that’s done offline and pushed on a periodic cycle. In the past month, we’ve pushed updated data for “Panda,” as we mentioned in a recent tweet. We’ve also made improvements to keep our database fresher overall.
- Live results for UEFA Champions League and KHL. We’ve added live-updating snippets in our search results for the KHL (Russian Hockey League) and UEFA Champions League, including scores and schedules. Now you can find live results from a variety of sports leagues, including the NFL, NBA, NHL and others.
- Tennis search feature. [launch codename "DoubleFault"] We’ve introduced a new search feature to provide realtime tennis scores at the top of the search results page. Try [maria sharapova] or [sony ericsson open].
- More relevant image search results. [launch codename "Lice"] This change tunes signals we use related to landing page quality for images. This makes it more likely that you’ll find highly relevant images, even if those images are on pages that are lower quality.
- Fresher image predictions in all languages. [launch codename "imagine2", project codename "Suggest"] We recently rolled out a change to surface more relevant image search predictions in autocomplete in English. This improvement extends the update to all languages.
- SafeSearch algorithm tuning. [launch codenames "Fiorentini", “SuperDyn”; project codename "SafeSearch"] This month we rolled out a couple of changes to our SafeSearch algorithm. We’ve updated our classifier to make it smarter and more precise, and we’ve found new ways to make adult content less likely to appear when a user isn't looking for it
- Tweaks to handling of anchor text. [launch codename "PC"] This month we turned off a classifier related to anchor text (the visible text appearing in links). Our experimental data suggested that other methods of anchor processing had greater success, so turning off this component made our scoring cleaner and more robust.
- Simplification to Images Universal codebase. [launch codename "Galactic Center"] We’ve made some improvements to simplify our codebase for Images Universal and to better utilize improvements in our general web ranking to also provide better image results.
- Better application ranking and UI on mobile. When you search for apps on your phone, you’ll now see richer results with app icons, star ratings, prices, and download buttons arranged to fit well on smaller screens. You’ll also see more relevant ranking of mobile applications based on your device platform, for example Android or iOS.
- Improvements to freshness in Video Universal. [launch codename "graphite", project codename "Freshness"] We’ve improved the freshness of video results to better detect stale videos and return fresh content.
- Fewer undesired synonyms. [project codename "Synonyms"] When you search on Google, we often identify other search terms that might have the same meaning as what you entered in the box (synonyms) and surface results for those terms as well when it might be helpful. This month we tweaked a classifier to prevent unhelpful synonyms from being introduced as content in the results set.
- Better handling of queries with both navigational and local intent. [launch codename "ShieldsUp"] Some queries have both local intent and are very navigational (directed towards a particular website). This change improves the balance of results we show, and helps ensure you’ll find highly relevant navigational results or local results towards the top of the page as appropriate for your query.
- Improvements to freshness. [launch codename "Abacus", project codename "Freshness"] We launched an improvement to freshness late last year that was very helpful, but it cost significant machine resources. At the time we decided to roll out the change only for news-related traffic. This month we rolled it out for all queries.
- Improvements to processing for detection of site quality. [launch codename "Curlup"] We’ve made some improvements to a longstanding system we have to detect site quality. This improvement allows us to get greater confidence in our classifications.
- Better interpretation and use of anchor text. We’ve improved systems we use to interpret and use anchor text, and determine how relevant a given anchor might be for a given query and website.
- Better local results and sources in Google News. [launch codename "barefoot", project codename "news search"] We’re deprecating a signal we had to help people find content from their local country, and we’re building similar logic into other signals we use. The result is more locally relevant Google News results and higher quality sources.
- Deprecating signal related to ranking in a news cluster. [launch codename "decaffeination", project codename "news search”] We’re deprecating a signal that’s no longer improving relevance in Google News. The signal was originally developed to help people find higher quality articles on Google News. (Note: Despite the launch codename, this project has nothing to do with Caffeine, our update to indexing in 2010).
- Fewer “sibling” synonyms. [launch codename "Gemini", project codename "Synonyms"] One of the main signals we look at to identify synonyms is context. For example, if the word “cat” often appears next to the term “pet” and “furry,” and so does the word “kitten”, our algorithms may guess that “cat” and “kitten” have similar meanings. The problem is that sometimes this method will introduce “synonyms” that actually are different entities in the same category. To continue the example, dogs are also “furry pets” -- so sometimes “dog” may be incorrectly introduced as a synonym for “cat”. We’ve been working for some time to appropriately ferret out these “sibling” synonyms, and our latest system is more maintainable, updatable, debuggable, and extensible to other systems.
- Better synonym accuracy and performance. [project codename "Synonyms"] We’ve made further improvements to our synonyms system by eliminating duplicate logic. We’ve also found ways to more accurately identify appropriate synonyms in cases where there are multiple synonym candidates with different contexts.
- Retrieval system tuning. [launch codename "emonga", project codename "Optionalization"] We’ve improved systems that identify terms in a query which are not necessarily required to retrieve relevant documents. This will make results more faithful to the original query.
- Less aggressive synonyms. [launch codename "zilong", project codename "Synonyms"] We’ve heard feedback from users that sometimes our algorithms are too aggressive at incorporating search results for other terms. The underlying cause is often our synonym system, which will include results for other terms in many cases. This change makes our synonym system less aggressive in the way it incorporates results for other query terms, putting greater weight on the original user query.
- Update to systems relying on geographic data. [launch codename "Maestro, Maitre"] We have a number of signals that rely on geographic data (similar to the data we surface in Google Earth and Maps). This change updates some of the geographic data we’re using.
- Improvements to name detection. [launch codename "edge", project codename "NameDetector"] We’ve improved a system for detecting names, particularly for celebrity names.
- Updates to personalization signals. [project codename "PSearch"] This change updates signals used to personalize search results.
- Improvements to Image Search relevance. [launch codename "sib"] We’ve updated signals to better promote reasonably sized images on high-quality landing pages.
- Remove deprecated signal from site relevance signals. [launch codename "Freedom"] We’ve removed a deprecated product-focused signal from a site-understanding algorithm.
- More precise detection of old pages. [launch codename "oldn23", project codename “Freshness"] This change improves detection of stale pages in our index by relying on more relevant signals. As a result, fewer stale pages are shown to users.
- Tweaks to language detection in autocomplete. [launch codename “Dejavu”, project codename "Suggest"] In general, autocomplete relies on the display language to determine what language predictions to show. For most languages, we also try to detect the user query language by analyzing the script, and this change extends that behavior to Chinese (Simplified and Traditional), Japanese and Korean. The net effect is that when users forget to turn off their IMEs, they’ll still get English predictions if they start typing English terms.
- Improvements in date detection for blog/forum pages. [launch codename "fibyen", project codename "Dates"] This change improves the algorithm that determines dates for blog and forum pages.
- More predictions in autocomplete by live rewriting of query prefixes. [launch codename "Lombart", project codename "Suggest”] In this change we’re rewriting partial queries on the fly to retrieve more potential matching predictions for the user query. We use synonyms and other features to get the best overall match. Rewritten prefixes can include term re-orderings, term additions, term removals and more.
- Expanded sitelinks on mobile. We’ve launched our expanded sitelinks feature for mobile browsers, providing better organization and presentation of sitelinks in search results.
- More accurate short answers. [project codename “Porky Pig”] We’ve updated the sources behind our short answers feature to rely on data from Freebase. This improves accuracy and makes it easier to fix bugs.
- Migration of video advanced search backends. We’ve migrated some backends used in video advanced search to our main search infrastructure.
- +1 button in search for more countries and domains. This month we’ve internationalized the +1 button on the search results page to additional languages and domains. The +1 button in search makes it easy to share recommendations with the world right from your search results. As we said in our initial blog post, the beauty of +1’s is their relevance—you get the right recommendations (because they come from people who matter to you), at the right time (when you are actually looking for information about that topic) and in the right format (your search results).
- Local result UI refresh on tablet. We’ve updated the user interface of local results on tablets to make them more compact and easier to scan.
- Unintentional algorithm change - Parked Domain Bug - April 16, 2012 - just to prove that they are "human", Google made a mistake with an algorithm modification. After a number of webmasters reported ranking shuffles, Google confirmed that a data error had caused some domains to be mistakenly treated as parked domains (and thereby devalued). This was not an intentional algorithm change.
- Panda 3.5 - April 19, 2012 - In the middle of a busy week for the algorthim, Google also quietly rolled out a Panda data update. This was a small update and appears to have been a fairly routine update with minimal impact.
- Google Penguin Update - April 24, 2012 - This was a major update that had been tested for some weeks leading up to the actual announcement. After weeks of speculation about an "Over-optimization penalty", Google finally rolled out the "Webspam Update", which was soon after dubbed "Penguin." Google Penguin adjusted a number of spam factors, including keyword stuffin and over-optimized anchor text and impacted an estimated 3.1% of English queries.
- Panda 3.6 - April 27, 2012 - Barely a week after Panda 3.5, Google rolled out yet another Panda data update. The implications of this update were unclear, and it seemed that the impact was relatively small.
- Categorize paginated documents. [launch codename "Xirtam3", project codename "CategorizePaginatedDocuments"] Sometimes, search results can be dominated by documents from a paginated series. This change helps surface more diverse results in such cases.
- More language-relevant navigational results. [launch codename "Raquel"] For navigational searches when the user types in a web address, such as [bol.com], we generally try to rank that web address at the top. However, this isn’t always the best answer. For example, bol.com is a Dutch page, but many users are actually searching in Portuguese and are looking for the Brazilian email service, http://www.bol.uol.com.br/. This change takes into account language to help return the most relevant navigational results.
- Country identification for webpages. [launch codename "sudoku"] Location is an important signal we use to surface content more relevant to a particular country. For a while we’ve had systems designed to detect when a website, subdomain, or directory is relevant to a set of countries. This change extends the granularity of those systems to the page level for sites that host user generated content, meaning that some pages on a particular site can be considered relevant to France, while others might be considered relevant to Spain.
- Anchors bug fix. [launch codename "Organochloride", project codename "Anchors"] This change fixed a bug related to our handling of anchors.
- More domain diversity. [launch codename "Horde", project codename "Domain Crowding"] Sometimes search returns too many results from the same domain. This change helps surface content from a more diverse set of domains.
- More local sites from organizations. [project codename "ImpOrgMap2"] This change makes it more likely you’ll find an organization website from your country (e.g. mexico.cnn.com for Mexico rather than cnn.com).
- Improvements to local navigational searches. [launch codename "onebar-l"] For searches that include location terms, e.g. [dunston mint seattle] or [Vaso Azzurro Restaurant 94043], we are more likely to rank the local navigational homepages in the top position, even in cases where the navigational page does not mention the location.
- Improvements to how search terms are scored in ranking. [launch codename "Bi02sw41"] One of the most fundamental signals used in search is whether and how your search terms appear on the pages you’re searching. This change improves the way those terms are scored.
- Disable salience in snippets. [launch codename "DSS", project codename "Snippets"] This change updates our system for generating snippets to keep it consistent with other infrastructure improvements. It also simplifies and increases consistency in the snippet generation process.
- More text from the beginning of the page in snippets. [launch codename "solar", project codename "Snippets"] This change makes it more likely we’ll show text from the beginning of a page in snippets when that text is particularly relevant.
- Smoother ranking changes for fresh results. [launch codename "sep", project codename "Freshness"] We want to help you find the freshest results, particularly for searches with important new web content, such as breaking news topics. We try to promote content that appears to be fresh. This change applies a more granular classifier, leading to more nuanced changes in ranking based on freshness.
- Improvement in a freshness signal. [launch codename "citron", project codename "Freshness"] This change is a minor improvement to one of the freshness signals which helps to better identify fresh documents.
- No freshness boost for low-quality content. [launch codename “NoRot”, project codename “Freshness”] We have modified a classifier we use to promote fresh content to exclude fresh content identified as particularly low-quality.
- Tweak to trigger behavior for Instant Previews. This change narrows the trigger area for Instant Previews so that you won’t see a preview until you hover and pause over the icon to the right of each search result. In the past the feature would trigger if you moused into a larger button area.
- Sunrise and sunset search feature internationalization. [project codename "sunrise-i18n"] We’ve internationalized the sunrise and sunset search feature to 33 new languages, so now you can more easily plan an evening jog before dusk or set your alarm clock to watch the sunrise with a friend.
- Improvements to currency conversion search feature in Turkish. [launch codename "kur", project codename "kur"] We launched improvements to the currency conversion search feature in Turkish. Try searching for [dolar kuru], [euro ne kadar], or [avro kaç para].
- Improvements to news clustering for Serbian. [launch codename "serbian-5"] For news results, we generally try to cluster articles about the same story into groups. This change improves clustering in Serbian by better grouping articles written in Cyrillic and Latin. We also improved our use of “stemming” -- a technique that relies on the “stem” or root of a word.
- Better query interpretation. This launch helps us better interpret the likely intention of your search query as suggested by your last few searches.
- News universal results serving improvements. [launch codename "inhale"] This change streamlines the serving of news results on Google by shifting to a more unified system architecture.
- UI improvements for breaking news topics. [launch codename "Smoothie", project codename "Smoothie"] We’ve improved the user interface for news results when you’re searching for a breaking news topic. You’ll often see a large image thumbnail alongside two fresh news results.
- More comprehensive predictions for local queries. [project codename "Autocomplete"] This change improves the comprehensiveness of autocomplete predictions by expanding coverage for long-tail U.S. local search queries such as addresses or small businesses.
- Improvements to triggering of public data search feature. [launch codename "Plunge_Local", project codename "DIVE"] This launch improves triggering for the public data search feature, broadening the range of queries that will return helpful population and unemployment data.
- Adding Japanese and Korean to error page classifier. [launch codename "maniac4jars", project codename "Soft404"] We have signals designed to detect crypto 404 pages (also known as “soft 404s”), pages that return valid text to a browser, but the text only contains error messages, such as “Page not found.” It’s rare that a user will be looking for such a page, so it’s important we be able to detect them. This change extends a particular classifier to Japanese and Korean.
- More efficient generation of alternative titles. [launch codename "HalfMarathon"] We use a variety of signals to generate titles in search results. This change makes the process more efficient, saving tremendous CPU resources without degrading quality.
- More concise and/or informative titles. [launch codename "kebmo"] We look at a number of factors when deciding what to show for the title of a search result. This change means you’ll find more informative titles and/or more concise titles with the same information.
- Fewer bad spell corrections internationally. [launch codename "Potage", project codename "Spelling"] When you search for [mango tea], we don't want to show spelling predictions like “Did you mean 'mint tea'?” We have algorithms designed to prevent these “bad spell corrections” and this change internationalizes one of those algorithms.
- More spelling corrections globally and in more languages. [launch codename "pita", project codename "Autocomplete"] Sometimes autocomplete will correct your spelling before you’ve finished typing. We’ve been offering advanced spelling corrections in English, and recently we extended the comprehensiveness of this feature to cover more than 60 languages.
- More spell corrections for long queries. [launch codename "caterpillar_new", project codename "Spelling"] We rolled out a change making it more likely that your query will get a spell correction even if it’s longer than ten terms. You can watch uncut footage of when we decided to launch this from our past blog post.
- More comprehensive triggering of “showing results for” goes international. [launch codename "ifprdym", project codename "Spelling"] In some cases when you’ve misspelled a search, say [pnumatic], the results you find will actually be results for the corrected query, “pneumatic.” In the past, we haven’t always provided the explicit user interface to say, “Showing results for pneumatic” and the option to “Search instead for pnumatic.” We recently started showing the explicit “Showing results for” interface more often in these cases in English, and now we’re expanding that to new languages.
- “Did you mean” suppression goes international. [launch codename "idymsup", project codename "Spelling"] Sometimes the “Did you mean?” spelling feature predicts spelling corrections that are accurate, but wouldn’t actually be helpful if clicked. For example, the results for the predicted correction of your search may be nearly identical to the results for your original search. In these cases, inviting you to refine your search isn’t helpful. This change first checks a spell prediction to see if it’s useful before presenting it to the user. This algorithm was already rolled out in English, but now we’ve expanded to new languages.
- Spelling model refresh and quality improvements. We’ve refreshed spelling models and launched quality improvements in 27 languages.
- Fewer autocomplete predictions leading to low-quality results. [launch codename "Queens5", project codename "Autocomplete"] We’ve rolled out a change designed to show fewer autocomplete predictions leading to low-quality results.
- Improvements to SafeSearch for videos and images. [project codename "SafeSearch"] We’ve made improvements to our SafeSearch signals in videos and images mode, making it less likely you’ll see adult content when you aren’t looking for it.
- Improved SafeSearch models. [launch codename "Squeezie", project codename "SafeSearch"] This change improves our classifier used to categorize pages for SafeSearch in 40+ languages.
- Improvements to SafeSearch signals in Russian. [project codename "SafeSearch"] This change makes it less likely that you’ll see adult content in Russian when you aren’t looking for it.
- Increase base index size by 15%. [project codename "Indexing"] The base search index is our main index for serving search results and every query that comes into Google is matched against this index. This change increases the number of documents served by that index by 15%. *Note: We’re constantly tuning the size of our different indexes and changes may not always appear in these blog posts.
- New index tier. [launch codename "cantina", project codename "Indexing"] We keep our index in “tiers” where different documents are indexed at different rates depending on how relevant they are likely to be to users. This month we introduced an additional indexing tier to support continued comprehensiveness in search results.
- Backend improvements in serving. [launch codename "Hedges", project codename "Benson"] We’ve rolled out some improvements to our serving systems making them less computationally expensive and massively simplifying code.
- "Sub-sitelinks" in expanded sitelinks. [launch codename "thanksgiving"] This improvement digs deeper into megasitelinks by showing sub-sitelinks instead of the normal snippet.
- Better ranking of expanded sitelinks. [project codename "Megasitelinks"] This change improves the ranking of megasitelinks by providing a minimum score for the sitelink based on a score for the same URL used in general ranking.
- Sitelinks data refresh. [launch codename "Saralee-76"] Sitelinks (the links that appear beneath some search results and link deeper into the site) are generated in part by an offline process that analyzes site structure and other data to determine the most relevant links to show users. We’ve recently updated the data through our offline process. These updates happen frequently (on the order of weeks).
- Less snippet duplication in expanded sitelinks. [project codename "Megasitelinks"] We’ve adopted a new technique to reduce duplication in the snippets of expanded sitelinks.
- Movie showtimes search feature for mobile in China, Korea and Japan. We’ve expanded our movie showtimes feature for mobile to China, Korea and Japan.
- MLB search feature. [launch codename "BallFour", project codename "Live Results"] As the MLB season began, we rolled out a new MLB search feature. Try searching for [sf giants score] or [mlb scores].
- Spanish football (La Liga) search feature. This feature provides scores and information about teams playing in La Liga. Try searching for [barcelona fc] or [la liga].
- Formula 1 racing search feature. [launch codename "CheckeredFlag"] This month we introduced a new search feature to help you find Formula 1 leaderboards and results. Try searching [formula 1] or [mark webber].
- Tweaks to NHL search feature. We’ve improved the NHL search feature so it’s more likely to appear when relevant. Try searching for [nhl scores] or [capitals score].
- Keyword stuffing classifier improvement. [project codename "Spam"] We have classifiers designed to detect when a website is keyword stuffing. This change made the keyword stuffing classifier better.
- More authoritative results. We’ve tweaked a signal we use to surface more authoritative content.
- Better HTML5 resource caching for mobile. We’ve improved caching of different components of the search results page, dramatically reducing latency in a number of cases.
- Google's Knowledge Graph - May 16, 2012 - In a major step toward semantic search, Google started rolling out "Knowledge Graph", a SERP-integrated display providing supplemental object about certain people, places, and things. Continue to expect to see "knowledge panels" appear on more and more SERPs over time.
- Penguin 1.1 - May 25, 2012 - Google rolled out its first targeted data update after the "Penguin" algorithm update. This confirmed that Penguin data was being processed outside of the main search index, much like Panda data.
- Deeper detection of hacked pages. [launch codename "GPGB", project codename "Page Quality"] For some time now Google has been detecting defaced content on hacked pages and presenting a notice on search results reading, “This site may be compromised.” In the past, this algorithm has focused exclusively on homepages, but now we’ve noticed hacking incidents are growing more common on deeper pages on particular sites, so we’re expanding to these deeper pages.
- Autocomplete predictions used as refinements. [launch codename "Alaska", project codename “Refinements”] When a user types a search she’ll see a number of predictions beneath the search box. After she hits “Enter”, the results page may also include related searches or "refinements". With this change, we’re beginning to include some especially useful predictions as “Related searches” on the results page.
- More predictions for Japanese users. [project codename "Autocomplete"] Our usability testing suggests that Japanese users prefer more autocomplete predictions than users in other locales. Because of this, we’ve expanded the number or predictions shown in Japan to as many as eight (when Instant is on).
- Improvements to autocomplete on Mobile. [launch codename "Lookahead", project codename "Mobile"] We made an improvement to make predictions work faster on mobile networks through more aggressive caching.
- Fewer arbitrary predictions. [launch codename "Axis5", project codename "Autocomplete"] This launch makes it less likely you’ll see low-quality predictions in autocomplete.
- Improved IME in autocomplete. [launch codename "ime9", project codename "Translation and Internationalization"] This change improves handling of input method editors (IMEs) in autocomplete, including support for caps lock and better handling of inputs based on user language.
- New segmenters for Asian languages. [launch codename "BeautifulMind"] Speech segmentation is about finding the boundaries between words or parts of words. We updated the segmenters for three asian languages: Chinese, Japanese, and Korean, to better understand the meaning of text in these languages. We’ll continue to update and improve our algorithm for segmentation.
- Scoring and infrastructure improvements for Google Books pages in Universal Search. [launch codename “Utgo”, project codename “Indexing”] This launch transitions the billions of pages of scanned books to a unified serving and scoring infrastructure with web search. This is an efficiency, comprehensiveness and quality change that provides significant savings in CPU usage while improving the quality of search results.
- Unified Soccer feature. [project codename "Answers"] This change unifies the soccer search feature experience across leagues in Spain, England, Germany and Italy, providing scores and scheduling information right on the search result page.
- Improvements to NBA search feature. [project codename "Answers"] This launch makes it so we’ll more often return relevant NBA scores and information right at the top of your search results. Try searching for [nba playoffs] or [heat games].
- New Golf search feature. [project codename "Answers"] This change introduces a new search feature for the Professional Golf Association (PGA) and PGA Tour, including information about tour matches and golfers. Try searching for [tiger woods] or [2012 pga schedule].
- Improvements to ranking for news results. [project codename "News"] This change improves signals we use to rank news content in our main search results. In particular, this change helps you discover news content more quickly than before.
- Better application of inorganic backlinks signals. [launch codename "improv-fix", project codename "Page Quality"] We have algorithms in place designed to detect a variety of link schemes, a common spam technique. This change ensures we’re using those signals appropriately in the rest of our ranking.
- Improvements to Penguin. [launch codename "twref2", project codename "Page Quality"] This month we rolled out a couple minor tweaks to improve signals and refresh the data used by the penguin algorithm.
- Trigger alt title when HTML title is truncated. [launch codename "tomwaits", project codename "Snippets"] We have algorithms designed to present the best possible result titles. This change will show a more succinct title for results where the current title is so long that it gets truncated. We’ll only do this when the new, shorter title is just as accurate as the old one.
- Efficiency improvements in alternative title generation. [launch codename "TopOfTheRock", project codename "Snippets"] With this change we’ve improved the efficiency of title generation systems, leading to significant savings in cpu usage and a more focused set of titles actually shown in search results.
- Better demotion of boilerplate anchors in alternate title generation. [launch codename "otisredding", project codename "Snippets"] When presenting titles in search results, we want to avoid boilerplate copy that doesn’t describe the page accurately, such as “Go Back.” This change helps improve titles by avoiding these less useful bits of text.
- Internationalizing music rich snippets. [launch codename "the kids are disco dancing", project codename "Snippets"] Music rich snippets enable webmasters to mark up their pages so users can more easily discover pages in the search results where you can listen to or preview songs. The feature launched originally on google.com, but this month we enabled music rich snippets for the rest of the world.
- Music rich snippets on mobile. [project codename "Snippets"] With this change we’ve turned on music rich snippets for mobile devices, making it easier for users to find songs and albums when they’re on the go.
- Improvement to SafeSearch goes international. [launch codename "GentleWorld", project codename "SafeSearch"] This change internationalizes an algorithm designed to handle results on the borderline between adult and general content.
- Simplification of term-scoring algorithms. [launch codename "ROLL", project codename "Query Understanding"] This change simplifies some of our code at a minimal cost in quality. This is part of a larger effort to improve code readability.
- Fading results to white for Google Instant. [project codename "Google Instant"] We made a minor user experience improvement to Google Instant. With this change, we introduced a subtle fade animation when going from a page with results to a page without.
- Better detection of major new events. [project codename "Freshness"] This change helps ensure that Google can return fresh web results in realtime seconds after a major event occurs.
- Smoother ranking functions for freshness. [launch codename "flsp", project codename "Freshness"] This change replaces a number of thresholds used for identifying fresh documents with more continuous functions.
- Better detection of searches looking for fresh content. [launch codename "Pineapples", project codename "Freshness"] This change introduces a brand new classifier to help detect searches that are likely looking for fresh content.
- Freshness algorithm simplifications. [launch codename “febofu", project codename "Freshness"] This month we rolled out a simplification to our freshness algorithms, which will make it easier to understand bugs and tune signals.
- Updates to +Pages in right-hand panel. [project codename “Social Search”] We improved our signals for identifying relevant +Pages to show in the right-hand panel.
- Performance optimizations in our ranking algorithm. [launch codename "DropSmallCFeature"] This launch significantly improves the efficiency of our scoring infrastructure with minimal impact on the quality of our results.
- Simpler logic for serving results from diverse domains. [launch codename "hc1", project codename "Other Ranking Components"] We have algorithms to help return a diverse set of domains when relevant to the user query. This change simplifies the logic behind those algorithms.
- Precise location option on tablet. [project codename “Mobile”] For a while you've had the option to choose to get personalized search results relevant to your more precise location on mobile. This month we expanded that choice to tablet. You’ll see the link at the bottom of the homepage and a button above local search results.
- Improvements to local search on tablet. [project codename “Mobile”] Similar to the changes we released on mobile this month, we also improved local search on tablet as well. Now you can more easily expand a local result to see more details about the place. After tapping the reviews link in local results, you’ll find details such as a map, reviews, menu links, reservation links, open hours and more.
- Internationalization of “recent” search feature on mobile. [project codename "Mobile"] This month we expanded the “recent” search feature on mobile to new languages and regions.
- Panda 3.7 - June 8, 2012 - Google rolled out yet another Panda data update, claiming that less than 1% of queries were affect.
- Panda 3.8 - June 25, 2012 - Google rolled out another Panda data refresh, but this appeared to be data only (no algorithm changes) and had a much smaller impact than Panda 3.7.
- Panda 3.9 - July 24, 2012 - A month after Panda 3.8, Google rolled out a new Panda update. Rankings fluctuated for 5-6 days, although no single day was high enough to stand out. Google claimed ~1% of queries were impacted.
- uefa-euro1. [project codename “Answers”] Addition of a live result showing schedule and scores of the EURO 2012 games (European championship of national soccer teams).
- #82293. [project codename “Answers”] Improved dictionary search feature by adding support for more natural language searches.
- Better HTML5 resource caching for mobile. [project codename “Mobile”] We’ve improved caching of different components of the search results page, dramatically reducing latency in a number of cases.
- ng2. [project codename “Other Ranking Components”] Better ordering of top results using a new and improved ranking function for combining several key ranking features.
- Ref-16. [project codename “Other Ranking Components”] Changes to an "official pages" algorithm to improve internationalization.
- Bamse. [project codename “Page Quality”] This launch helps you find more high-quality content from trusted sources.
- Bamse-17L. [project codename “Page Quality”] This launch helps you find more high-quality content from trusted sources.
- GreenLandII. [project codename “Page Quality”] We've incorporated new data into the Panda algorithm to better detect high-quality sites and pages.
- #82353. [project codename “Page Quality”] This change refreshes data for the Panda high-quality sites algorithm.
- SuperQ2. [project codename “Image”] We've updated a signal for Google Images to help return more on-topic image search results.
- #82743. [project codename “Answers”] Changes to the calculator feature to improve recognition of queries containing "and," such as [4 times 3 and a half].
- komodo. [project codename “Query Understanding”] Data refresh for system used to better understand and search for long-tail queries.
- #82580. [project codename “Answers”] This is an improvement for showing the sunrise and sunset times search feature.
- PitCode. [project codename “Answers”] This launch adds live results for Nascar, MotoGP, and IndyCar. This is in addition to Formula1 results, which were already available.
- timeob. [project codename “Answers”] We've improved natural language detection for the time feature to better understand questions like, "What time is it in India?"
- #81933. [project codename “Synonyms”] This launch improves use of query synonyms in ranking. Now we're less likely to show documents where the synonym has a different meaning than the original search term.
- #82496. [project codename “Answers”] Changes made to the movie showtimes feature on mobile to improve recognition of natural language queries and overall coverage.
- #82367. [project codename “Other Ranking Components”] This launch helps you find more high-quality content from trusted sources.
- #82699. [project codename “Other Search Features”] We've made it easier to quickly compare places. Now you can hover over a local result and see information about that place on the right-hand side.
- CapAndGown. [project codename “Image”] On many webpages, the most important images are closely related to the overall subject matter of the page. This project helps you find these salient images more often.
- #82769. [project codename “Answers”] Improvements to the calculator feature on mobile to improve handling of queries that contain both words and numbers such as [4 times 3 divided by 2].
- Vuvuzela. [project codename “SafeSearch”] We've updated SafeSearch to unify the handling of adult video content in videos mode and in the main search results. Explicit video thumbnails are now filtered more consistently.
- #82537. [project codename “Answers”] We've enabled natural language detection for the currency conversion feature to better understand questions like, "What is $500 in euros?"
- #82519. [project codename “Answers”] We've enabled natural language detection for the flight status feature to better understand questions about flight arrival times and status.
- #82879. [project codename “Answers”] We've improved the triggering for the "when is" feature and understanding of queries like, "When is Mother's Day?"
- wobnl0330. [project codename “Answers”] Improvements to display of the weather search feature.
- Lime. [project codename “Freshness”] This change improves the interaction between various search components to improve search results for searches looking for fresh content.
- gas station. [project codename “Snippets”] This change removes the boilerplate text in sitelinks titles, keeping only the information useful to the user.
- #81776. [project codename “Answers”] We've improved natural language detection for the unit conversion feature to better understand questions like, "What is 5 miles in kilometers?"
- #81439. [project codename “Answers”] Improved display of the finance feature for voice search queries on mobile.
- #82666. [project codename “Page Quality”] This launch helps you find more high-quality content from trusted sources.
- #82541. [project codename “Other Ranking Components”] This is one of multiple projects that we're working on to make our system for clustering web results better and simpler.
- gaupe. [project codename “Universal Search”] Improves display of the flights search feature. Now, this result shows for queries with destinations outside the US, such as [flights from Austin to London].
- #82887. [project codename “Answers”] We've improved natural language processing for the dictionary search feature.
- gallium-2. [project codename “Synonyms”] This change improves synonyms inside concepts.
- zinc-4. [project codename “Synonyms”] This change improves efficiency by not computing synonyms in certain cases.
- Manzana2. [project codename “Snippets”] This launch improves clustering and ranking of links in the expanded sitelinks feature.
- #82921. [project codename “Alternative Search Methods”] We've improved finance results to better understand finance-seeking queries spoken on mobile.
- #82936. [project codename “Answers”] Improved display of the weather search feature, so you can ask [weather in california] or [is it hot in italy].
- #82935. [project codename “Answers”] We've improved natural language detection for the sunrise/sunset feature.
- #82460. [project codename “Snippets”] With this change we're using synonyms to better generate accurate titles for web results.
- #82953. [project codename “Answers”] This change improves detection of queries about weather.
- PandaMay. [project codename “Search Quality”] We launched a data refresh for our Panda high-quality sites algorithm.
- ItsyBitsy. [project codename “Images”] To improve the quality of image results, we filter tiny, unhelpful images at the bottom of our image results pages.
- localtimeob. [project codename “Answers”] We've improved display of the local time search feature.
- #82536. [project codename “Answers”] We've improved natural language detection to better understand queries about baseball and return the latest baseball information about MLB, such as schedules and the latest scores.
- Improvements to Images Universal ranking. [project codename “Universal Search”] We significantly improved our ability to show Images Universal on infrequently searched-for queries.
- absum3. [project codename “Snippets”] This launch helps us select better titles to display in the search results. This is a change to our algorithm that will specifically improve the titles for pages that are in non-Latin based languages.
- #83051. [project codename “Answers”] We've improved display of local business information in certain mobile use cases. In particular, we'll highlight information relevant to the search, including phone numbers, addresses, hours and more.
- calc2-random. [project codename “Answers”] This change improves our understanding of calculator-seeking queries.
- #82961. [project codename “Alternative Search Methods”] When you search for directions to or from a location on your mobile device without specifying the start point, we'll return results starting from your current position.
- #82984. [project codename “Universal Search”] This was previously available for users searching on google.com in English, and now it's available for all users searching in English on any domain.
- #82150. [project codename “Spelling”] Refresh of our algorithms for spelling systems in eight languages.
- NoPathsForClustering. [project codename “Other Ranking Components”] We've made our algorithm for clustering web results from the same site or same path (same URL up until the last slash) more consistent. This is one of multiple projects that we're working on to make our clustering system better and simpler.
- Hamel. [project codename “Page Quality”] This change updates a model we use to help you find high-quality pages with unique content.
- #81977. [project codename “Synonyms”] This change updates our synonyms systems to make it less likely we'll return adult content when users aren't looking for it.
- Homeland. [project codename “Autocomplete”] This is an improvement to autocomplete that will help users to get predicted queries that are more relevant to their local country.
- #82948. [project codename “Other Search Features”] We've improved our natural language processing to improve display of our movie showtimes feature.
- yoyo. [project codename “Snippets”] This change leads to more useful text in sitelinks.
- popcorn. [project codename “Snippets”] We've made a minor update to our algorithm that detects if a page is an "article." This change facilitates better snippets.
- Golden Eagle. [project codename “Autocomplete”] When Google Instant is turned off, we'll sometimes show a direct link to a site in the autocomplete predictions. With this change we refreshed the data for those predictions.
- #82301. [project codename “Indexing”] This change improves an aspect of our serving systems to save capacity and improve latency.
- #82392. [project codename “Indexing”] This launch improves the efficiency of the Book Search ranking algorithms, making them more consistent with Web Search.
- Challenger. [project codename “Snippets”] This is another change that will help get rid of generic boilerplate text in Web results' titles, particularly for sitelinks.
- #83166. [project codename “Universal Search”] This change is a major update to Google Maps data for the following regions: CZ, GR, HR, IE, IT, VA, SM, MO,PT, SG, LS. This new data will appear in maps universal results.
- #82515. [project codename “Translation and Internationalization”] This change improves the detection of queries that would benefit from translated results.
- bergen. [project codename “Other Ranking Components”] This is one of multiple projects that we're working on to make our system for clustering web results better and simpler.
- Panda JK. [project codename “Page Quality”] We launched Panda on google.co.jp and google.co.kr to promote more high-quality sites for users in Japan and Korea.
- rrfix4. [project codename “Freshness”] This is a bug fix to a freshness algorithm. This change turns off a freshness algorithm component in certain cases when it should not be affecting the results.
- eventhuh4. [project codename “Knowledge Graph”] We'll show a list of upcoming events in the Knowledge Graph for city-related searches such as [san francisco] and [events in san francisco].
- #83483. [project codename “Universal Search”] This change helps surface navigation directions directly in search results for more queries.
- Zivango. [project codename “Refinements”] This change leads to more diverse search refinements.
- #80568. [project codename “Snippets”] This change improves our algorithm for generating site hierarchies for display in search result snippets.
- Labradoodle. [project codename “SafeSearch”] We've updated SafeSearch algorithms to better detect adult content.
- JnBamboo. [project codename “Page Quality”] We’ve updated data for our Panda high-quality sites algorithm.
- #83242. [project codename “Universal Search”] This change improves news universal display by using entities from the Knowledge Graph.
- #75921. [project codename “Autocomplete”] For some time we've shown personalized predictions in Autocomplete for users who've enabled Web History on google.com in English. With this change, we're internationalizing the feature.
- #83301. [project codename “Answers”] Similar to the live results we provide for sports like baseball or European football, you can now search on Google and find rich, detailed information about the latest schedule, medal counts, events, and record-breaking moments for the world's largest sporting spectacle.
- #83432. [project codename “Autocomplete”] This change helps users find more fresh trending queries in Japanese as part of autocomplete.
- DMCA Penalty - August 10, 2012 - Google announced that they would start penalizing sites with repeat copyright violations, probably via DMCA takedown requests.
- 7-Result SERPs — August 14, 2012 - Google made a significant change to the Top 10, limiting it to 7 results for many queries as many as 20% of queries that were tested saw this change.
- Panda 3.9.1 - August 20, 2012 - Google rolled out yet another Panda data update, but the impact seemed to be fairly small. Since the Panda 3.0 series ran out of numbers at 3.9, the new update was dubbed 3.9.1.
- Panda 3.9.2 - September 18, 2012 - Google rolled out another Panda refresh, which appears to have been data-only. Ranking flux was moderate but not on par with a large-scale algorithm update.
- Panda #20 - September 27, 2012 - Overlapping the EMD update, a fairly major Panda update (algo + data) rolled out, officially affecting 2.4% of queries. As the 3.X series was getting odd, industry sources opted to start naming Panda updates in order (this was the 20th).
- Exact-Match Domain (EMD) Update - September 27, 2012 - Google announced a change in the way it was handling exact-match domains (EMDs). This led to large-scale devaluation, reducing the presence of EMDs in the MozCast data set by over 10%. Official word is that this change impacted 0.6% of queries (by volume).
- #82862. [project “Page Quality”] This launch helped you find more high-quality content from trusted sources.
- #83197. [project “Autocomplete”] This launch introduced changes in the way we generate query predictions for Autocomplete.
- #83818. [project “Answers”] This change improved display of the movie showtimes feature.
- #83819. [project “Answers”] We improved display of the MLB search feature.
- #83820. [project “Answers”] This change improved display of the finance search feature.
- #83384. [project “Universal Search”] We made improvements to driving directions in Turkish.
- #83459. [project “Alternative Search Methods”] We added support for answers about new stock exchanges for voice queries.
- LTS. [project “Other Ranking Components”] We improved our web ranking to determine what pages are relevant for queries containing locations.
- Maru. [project “SafeSearch”] We updated SafeSearch to improve the handling of adult video content in videos mode for queries that are not looking for adult content.
- #83135. [project “Query Understanding”] This change updated term-proximity scoring.
- #83659. [project “Answers”] We made improvements to display of the local time search feature.
- #83105. [project “Snippets”] We refreshed data used to generate sitelinks.
- Imadex. [project “Freshness”] This change updated handling of stale content and applies a more granular function based on document age.
- #83613. [project “Universal Search”] This change added the ability to show a more appropriately sized video thumbnail on mobile when the user clearly expresses intent for a video.
- #83443. [project “Knowledge Graph”] We added a lists and collections component to the Knowledge Graph.
- #83442. [project “Snippets”] This change improved a signal we use to determine how relevant a possible result title actually is for the page.
- #83012. [project “Knowledge Graph] The Knowledge Graph displays factual information and refinements related to many types of searches. This launch extended the Knowledge Graph to English-speaking locales beyond the U.S.
- #84063. [project “Answers”] We added better understanding of natural language searches for the calculator feature, focused on currencies and arithmetic.
- nearby. [project “User Context”] We improved the precision and coverage of our system to help you find more relevant local web results. Now we’re better able to identify web results that are local to the user, and rank them appropriately.
- essence. [project “Autocomplete”] This change introduced entity predictions in autocomplete. Now Google will predict not just the string of text you might be looking for, but the actual real-world thing. Clarifying text will appear in the drop-down box to help you disambiguate your search.
- #83821. [project “Answers”] We introduced better natural language parsing for display of the conversions search feature.
- #82279. [project “Other Ranking Components”] We changed to fewer results for some queries to show the most relevant results as quickly as possible.
- #82407. [project “Other Search Features”] For pages that we do not crawl because of robots.txt, we are usually unable to generate a snippet for users to preview what's on the page. This change added a replacement snippet that explains that there's no description available because of robots.txt.
- #83709. [project “Other Ranking Components”] This change was a minor bug fix related to the way links are used in ranking.
- #82546. [project “Indexing”] We made back-end improvements to video indexing to improve the efficiency of our systems.
- Palace. [project “SafeSearch”] This change decreased the amount of adult content that will show up in Image Search mode when SafeSearch is set to strict.
- #84010. [project “Page Quality”] We refreshed data for the "Panda" high-quality sites algorithm.
- #84083. [project “Answers”] This change improved the display of the movie showtimes search feature.
- gresshoppe. [project “Answers”] We updated the display of the flight search feature for searches without a specified destination.
- #83670. [project “Snippets”] We made improvements to surface fewer generic phrases like "comments on" and "logo" in search result titles.
- #83777. [project “Synonyms”] This change made improvements to rely on fewer "low-confidence" synonyms when the user's original query has good results.
- #83377. [project “User Context”] We made improvements to show more relevant local results.
- #83484. [project “Refinements”] This change helped users refine their searches to find information about the right person, particularly when there are many prominent people with the same name.
- #82872. [project “SafeSearch”] In "strict" SafeSearch mode we remove results if they are not very relevant. This change previously launched in English, and this change expanded it internationally.
- Knowledge Graph Carousel. [project “Knowledge Graph”] This change expanded the Knowledge Graph carousel feature globally in English.
- Sea. [project “SafeSearch”] This change helped prevent adult content from appearing when SafeSearch is in "strict" mode.
- #84259. [project “Autocomplete”] This change tweaked the display of real-world entities in autocomplete to reduce repetitiveness. With this change, we don't show the entity name (displayed to the right of the dash) when it's fully contained in the query.
- TSSPC. [project “Spelling”] This change used spelling algorithms to improve the relevance of long-tail autocomplete predictions.
- #83689. [project “Page Quality”] This launch helped you find more high-quality content from trusted sources.
- #84068. [project “Answers”] We improved the display of the currency conversion search feature.
- #84586. [project “Other Ranking Components”] This change improved how we rank documents for queries with location terms.
- Dot. [project “Autocomplete”] We improved cursor-aware predictions in Chinese, Japanese and Korean languages. Suppose you're searching for "restaurants" and then decide you want "Italian restaurants." With cursor-aware predictions, once you put your cursor back to the beginning of the search box and start typing "I," the prediction system will make predictions for "Italian," not completions of "Irestaurants."
- #84288. [project “Autocomplete”] This change made improvements to show more fresh predictions in autocomplete for Korean.
- trafficmaps. [project “Universal Search”] With this change, we began showing a traffic map for queries like "traffic from A to B" or "traffic between A and B."
- #84394. [project “Page Quality”] This launch helped you find more high-quality content from trusted sources.
- #84652. [project “Snippets”] We currently generate titles for PDFs (and other non-html docs) when converting the documents to HTML. These auto-generated titles are usually good, but this change made them better by looking at other signals.
- #83761. [project “Freshness”] This change helped you find the latest content from a given site when two or more documents from the same domain are relevant for a given search query.
- #83406. [project “Query Understanding”] We improved our ability to show relevant Universal Search results by better understanding when a search has strong image intent, local intent, video intent, etc.
- espd. [project “Autocomplete”] This change provided entities in autocomplete that are more likely to be relevant to the user's country. See blog post for background.
- #83391. [project “Answers”] This change internationalized and improved the precision of the symptoms search feature.
- #82876. [project “Autocomplete”] We updated autocomplete predictions when predicted queries share the same last word.
- #83304. [project “Knowledge Graph”] This change updated signals that determine when to show summaries of topics in the right-hand panel.
- #84211. [project “Snippets”] This launch led to better snippet titles.
- #81360. [project “Translation and Internationalization”] With this launch, we began showing local URLs to users instead of general homepages where applicable (e.g. blogspot.ch instead of blogspot.com for users in Switzerland). That’s relevant, for example, for global companies where the product pages are the same, but the links for finding the nearest store are country-dependent.
- #81999. [project “Translation and Internationalization”] We revamped code for understanding which documents are relevant for particular regions and languages automatically (if not annotated by the webmaster).
- Cobra. [project “SafeSearch”] We updated SafeSearch algorithms to better detect adult content.
- #937372. [project “Other Search Features”] The translate search tool is available through the link "Translated foreign pages" in the sidebar of the search result page. In addition, when we guess that a non-English search query would have better results from English documents, we'll show a feature at the bottom of the search results page to suggest users try the translate search tool. This change improved the relevance of when we show the suggestion.
- #84460. [project “Snippets”] This change helped to better identify important phrases on a given webpage.
- #80435. [project “Autocomplete”] This change improves autocomplete predictions based on the user's Web History (for signed-in users).
- #83901. [project “Synonyms”] This change improved the use of synonyms for search terms to more often return results that are relevant to the user's intention.
- Penguin #3 - October 5, 2012 - After suggesting the next Penguin update would be major, Google released a minor Penguin data update, impacting "0.3% of queries". Penguin update numbering was rebooted, similar to Panda - this was the 3rd Penguin release.
- Page Layout #2 - October 9, 2012 - Google announced an update to its original page layout algorithm change back in January, which targeted pages with too many ads above the fold. It's unclear whether this was an algorithm change or a Panda-style data refresh.
Some of you may find chasing the algorithm fascinating, after all people have tried to reverse engineer Google's algorithms for years. The fact is Google continues to try and improve their Search product and you have to appluad them for that. It is probably that reason as to why they remain the number one search engine in the world. While they could use a little more competition and while some of their results are still "broken", you have to give them credit from trying to organize the worlds information. If you had access to over a trillion web pages what would you do?
Labels: Google algorithm, Google algorithm updates
|posted by Jody @ 7:17 PM