Is Facebook planning on sharing information about the words that people use on the site in messages, and demographics about the people behind those messages? A couple of patent applications published today at the US Patent and Trademark Office describe how the social network might analyze the messages of members, to identify popular topics and the words that co-occur in messages that contain references to those topics. They also describe how demographic information supplied by members might be used to graph those topics.
The following images are a couple of examples of one way that kind of information might be displayed (click on the images to see larger versions). The first displays mentions of President Obama from messages dating back 14 days from July 21, 2008, along with many of the most popular words or phrases that accompanied those messages, as well as information about what percentage of those mentions came from males graphed against the average age of those members. Topics displayed by this system can cover a wide range of topics included in Facebook messages, as the second image shows mentioning “Hip hop,” along with popular terms included in those messages.
The patent filing descriptions begin with a discussion of the limitations of opinion polls, surveys, and focus groups. They go on to tell us how those shortcomings might be solved by mining data from messages sent by members of a social network and analyzing demographic information associated with those members.
One question I had when I started reading these patent filings is where might Facebook get the topics to collect information about? Another was who would be shown this topic and demographic information?
It appears that the topics may be supplied by advertisers. One of the images accompanying the patents shows a flowchart which identifies advertisers as a source of topics:
The patent applications are:
Displaying Demographic Information of Members Discussing Topics in a Forum
US Patent Application 20100164957
Tracking Significant Topics of Discourse in Forums
US Patent Application 20100169327
Invented by Robert Taaffe Lindsay and Blaise Andrew DiPersia
Assigned to Facebook, Inc.
Published July 1, 2010
Filed December 31, 2008
Users in public forums often mention certain topics in the course of their discussions. Member’s comments in messages to other members are analyzed to obtain terms that co-occur with topics. Frequencies of co-occurrence of a term with topics are normalized based on frequency of the term in a random sample of message.
The terms are ranked by their normalized frequency of co-occurrence with a topic in messages. The top terms are selected based on their rank.
Analysis of demographic information associated with members that mentioned top terms associated with a topic is displayed in graphical format that highlights the relationship between the age, gender, and usage of the top terms over time. The demographic information presented includes average age of members that mentioned a top term or their gender information within a selected time interval.
The patent applications provide more details on how topic information data might be collected, and how “top terms” related to topics might be identified based upon topics selected by advertisers:
All terms that co-occur with a given topic can be ranked by their respective normalized co-occurrence frequency values. The top ranked terms are selected and are deemed the significant terms of interest to the advertiser that provided the topic and are called “top terms.”
We aren’t told if this demographic information would only be displayed to advertisers, or if it would also be available to members of the social network.
The images above about President Obama and Hip Hop are examples of one way that information might be displayed.
Displaying trend data over time is another possibility.
The inventors tell us that other demographic information could be used as well, such as:
- Language spoken
- Education level
- Relative distance from a predetermined location such as the distance of a member’s residence from the downtown of a city
- Number of social connections of a member
How does this make you feel about Facebook?