An Overview of the Changes and Advances in Facebook Entity Graph
July 4, 2013
The article on TNW titled How Facebook’s Entity Graph Evolved From Plain Text to the Structured Data That Powers Graph Search explores the timeline of Facebook’s ability to understand and make connections between billions of pieces of information about its billions of users. Eric Sun, Facebook’s software engineer, recently posted about the evolution of the Entity Graph on the Facebook Blog. Entity graph led to Social Graph, which eventually enabled the Graph Search. The article explains,
“In order to take advantage of all of those juicy details in your profile, Sun said his team had to find a data set to represent a seemingly unlimited number of interests. Their solution was to tap into Wikipedia, which powered Facebook’s creation of “millions of ‘fallback’ pages.” Facebook heavily relies on Wikipedia to this day. These fallback pages were matched to interests that couldn’t be connected to pre-existing pages. Afterwards, they were manually vetted for duplicates; ones which didn’t receive any connections were deleted.”
Today, Sun claims the Entity Graph is growing even faster than Facebook can keep up with. The focus of his team is now to improve the graph further. We have all witnessed the changes made to Facebook over the last ten years, but most of the reactions have been to the aesthetic qualities of the pages we think of as our own. The reason behind many of the changes was to incorporate the mapping of our interests and our lives, to allow Facebook to know more.
Chelsea Kerwin, July 04, 2013
Sponsored by ArnoldIT.com, developer of Augmentext.
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
