'Net Features : graph search

Facebook Graph Search Secrets Revealed

Michael Garrity — Wed, 20 Mar 2013 19:00:00 GMT

Late last week, the Facebook team wrote a blog post that let users “under the hood” to show them how Graph Search goes about indexing and ranking search query results on the social network.

Knowingly or not, what Facebook really did was reveal the secrets of social media optimization. Since "knowing" how things work is half the digital battle, let's dig into the details to accelerate your future Facebook (and more specifically Graph Search) success.

Graph Search and You
Of all of the information released in the blog post (and there is a lot), perhaps the most important and useful of it all is that Facebook is not only going to use Graph Search to find data, but also to build upon it and include new features that will quantify important elements of a search query to provide the most relevant information based on factors unique to a particular query. This includes the distance between a searcher and a place, how close a searcher is from user results in terms of friend connections and the amount of overlap a query may have with an entity name, among others. In other words, naming things right and having many friends are both great ways to improve your Facebook page’s performance when it comes to graph search results.

If you care about social media optimization at all, use this information as a digital blueprint for a successful Facebook presence in Graph Search results.

In the future, this could mean that an entity (person, place, etc.) will have several different scores assigned to it, and Graph Search can select the top results based on those score. So, for instance, there could be three different scores for a “nearby” search that account for overall popularity, social bias and distance, thus allowing for greater diversity and more relevance in search results that are, ultimately, more useful for those searching, as well as those being searched for.

Let's Get Technical
It appears that Facebook uses a blending of data-driven techniques and “intuition” to rank the best results for a query by coming up with an idea for a ranking change (based on information from both ranking engineers and user feedback), implementing it, testing it and then launching it to a small fraction of users before measuring the impact it has on ranking changes. And it all starts with Unicorn.

Unicorn is an index framework and in-memory database that lets users (Facebook, in this case) create various vertical databases to house specific information, and then use a query language to retrieve that information later. However, before Facebook could begin to utilize Unicorn for Graph Search, the company had to add to its search ranking capabilities by adding things like query rewrites, forward indexing, A/B testing and extended retrieval operations with weak “and” and strong “or” recognition, in addition a number of other changes.

The Graph Search Lifecycle
All of these modifications serve Graph Search at different points throughout a query’s lifecycle, which largely takes place in two distinct phases: the query suggestion phase and the search phase. In the query suggestion phase, the query that a user types into the search box is parsed based on grammar by a Natural Language Processing (NLP) module, which then identifies the query for potential entities, before sending them along to Unicorn to conduct a search for them.

This is perhaps the most important step in the whole process, as it defines what type of entity the searcher may be looking for, thus signaling where Unicorn should look for the information, as Facebook altered the index framework to keep different entity types in separate verticals. In other words, it tells Unicorn what kind of results to present. For example, if a user types in “people who live in Sri,” the query will be sent with a strong bias toward cities and places, meaning location-based results will be more likely to appear because of the particular grammar qualifications of the query.

The search phase begins after a user had made a selection from Graph Search’s suggestions. Again, all of this new information is sent back to Unicorn via the “Top Aggregator,” which takes in raw query and user metadata information and then represents it at the end as the blended and rescored search results. This is where Graph Search is able to narrow down the original query to provide only relevant results unique to a user’s search. In addition, Graph Search is able to rewrite queries into a social context to bias the results socially, as every user is indexed with his or her friends.

Facebook's News Feed Gets Personal

Michael Garrity — Fri, 08 Mar 2013 19:45:00 GMT

For the first time since 2006, more or less, Facebook has finally made some massive changes to its news feed, giving it a new look and enhanced functionality to act more like a “personalized newspaper.”

Perhaps the biggest change to come from Facebook’s facelift, or at least the most noticeable, is a clear image-heavy focus. Now, news “stories” are going to be much more visual, which is in line with the type of content that social media users tend to favor sharing and engaging with. Images will be larger and more heavily emphasized, taking up almost half of all news feed stories. Bigger photos will also be accentuated with a cleaner, easier-to-navigate design.

Although images are getting all of the attention, the more useful upgrade to the news feed is that users now have access to an even greater number of feeds with specific types of content; they will also be given more control over how those feeds are displayed. For instance, a user can subscribe a to new type of news feed (such as All Friends, Close Friends, Photos, Games, Music, etc.) that will only show posts from certain individuals or that feature a certain kind of content. Plus, these news feeds will (finally) feature an option to view posts chronologically.

And last, but not least, the news feeds are going to be compatible with mobile devices; in fact, they were built with mobile users top-of-mind. Many will notice that it looks quite similar to Facebook’s mobile applications, as it features a side navigation bar and a lot more white space. The new news feeds will help provide a much more consistent user experience across multiple platforms and devices.

Of course, many of you are probably wondering what effect these changes will have on your business, especially as it relates to promoted posts or sponsored stories. Well, the fact is we just don’t know, yet (this was all just announced yesterday, after all), but Chris Marentis, founder and CEO of Surefire Social, thinks that there are two important things that business owners on the Web should remember.

The first is that all of these social media technologies, including Facebook, are still young and “will continue to change and evolve over time.” But that being said, he still thinks that they can provide a great opportunity right now for your brand to reach out to and engage with your target audience in a way that was heretofore impossible for most companies.

In addition to that, he said, “Whatever changes Facebook makes are in an effort to be more advertiser-friendly without disturbing their relationship with the users. They want to maintain the integrity of the user experience. Also, the changes that Facebook has made recently, particularly with the introduction of Graph Search, prove that the company is serious about advertising, as well as search and discovery for businesses on the platform. As a business owner, you should want to be on top of and taking advantage of these changes.”

Facebook Offers Graph Search Insights/Suggestions

Allison Howen — Tue, 05 Mar 2013 19:15:00 GMT

Since Facebook’s launch of Graph Search, there has been a lot of speculation of how this feature will influence people’s search habits both on and off the world’s largest social network.

Although Graph Search is still in beta and currently only available to select users, Facebook has unveiled some insights into how those who already have the new search feature are utilizing it. The insights reveal that most people are using Graph Search to look up friends (in the same way they did with Facebook's original search feature), followed by those who leverage the feature to find photos, plan trips and discover new things. While this basic use of the new search feature is not surprising, Facebook is also offering some search suggestions to help people discover other ways to take advantage of Graph Search.

For example, although many people are leveraging Graph Search to find pictures of friends and family, Facebook suggests that members use Graph Search to discover public images from brands or news organizations. This can be done with a simple search like “Photos by National Geographic.” Moreover, members can use Graph Search to plan activities with search queries like “Ski resorts my friends have been to” or “Hotels near Museum of Fine Arts, Boston.”

These insights and suggestions that come directly from Facebook seem to imply that the social network's members are typically not using Graph Search beyond basic searches for finding people or Pages – as they did with the social network’s original search offering. This could pose a problem for Facebook, because even though Graph Search has the potential to shake up the local discovery and search industries, doesn’t mean it will. This is especially true if members aren’t aware of how to use the feature or are simply not using it to its full potential.

Facebook's search suggestions further prove how important it is for brands to maintain an engaging Page on Facebook, which can be accomplished through posting a variety of content and fostering interactions with fans. By doing this, brands will have a better chance of showing up in the results when members conduct searches for public images or for places that their friends have been to or liked.

Facebook’s Graph Search, 5 Oughta Knows

Allison Howen — Wed, 16 Jan 2013 19:20:00 GMT

The world’s largest social network made waves on the ’Net yesterday with the launch of a new tool called Graph Search.

The tool essentially allows people to discover information based on data that Facebook has collected from its users over time. For example, someone could use Graph Search to discover information such as “restaurants in Chicago that my friends like” or “photos of me that I liked.”

While Graph Search is currently in a limited beta release, the tool seems to improve the social network’s lackluster search bar, which previously only allowed users to search for people or pages on the social network. Moreover, Graph Search has the potential to impact businesses on Facebook. Discover five things you should know about Graph Search below:

1. Likes Matter

Facebook Likes are now more important than ever, especially for businesses. According to a Facebook blog post, Graph Search can make it easier for people to discover and learn more about businesses on Facebook. This is because the search results are based on Facebook’s robust database, which includes information that has been shared by businesses and individuals alike. That being said, businesses with a large fan base will be more likely to turn up in searches for phrases like “restaurants in Chicago that my friends like.”

2. Engagement is Key

Aside from obtaining likes, businesses should focus on maintaining an engaging Page that includes quality interactions with fans. Since the search results are based on information that has been shared by businesses and individuals, interactions between a business and their fans can help the business score higher in the search results. Furthermore, Graph Search also makes interactions like check-ins even more important, because users could potentially search for phrases like “Places in Los Angeles that my friends have been to.”

3. Invest in your Page

Facebook’s blog post states that the best thing businesses can do for their Page is to continue to invest in it and make sure that it is complete and up-to-date. Items like the name, category, vanity URL and information within the “About” section of a business Page can help make it easier for people to find the business on Facebook. Additionally, Page owners should make sure that their business's address is correct because this information could help someone discover a local business when they are searching for places in a specific location.

4. There are No Graph Search Ad Formats…Yet

As Graph Search becomes more widely available, so will the speculation of a new ad format from Facebook. However, the social network confirmed in their blog post that there are currently no new ad formats available for Graph Search. However, it is important to note that Pages and apps can still use the Sponsored Results ad format to show up in the search results for all Facebook users, whether they have Graph Search or not.

5. Sign Up to Try It

Graph Search is currently in a limited beta release, which means that you must sign up for a waitlist to gain access to this tool. According to Facebook, the rollout of Graph Search will be gradual, starting with a very small number of users. This means that the company is still working out some of the bugs in order to provide the best search results possible to its users before the tool is available to everyone.