Inside Facebook

Facebook, as is readily obvious by now, has an inordinate amount of data about its 150 million users: who they are, where they live, what they like, who they know, and what they say. But could new research the company is conducting on user-generated data let the company know how they feel?

In a conversation last week with prominent blogger Robert Scoble in Davos, Switzerland, Facebook CEO Mark Zuckerberg described work Facebook is doing on “sentiment” research, and what that could mean for the future of Facebook. According to Scoble,

Facebook is, he told me, studying “sentiment” behavior. It hasn’t yet used that research in its public service yet, but is looking to figure out if people are having a good day or bad day. He said that already his teams are able to sense when nasty news, like stock prices are headed down, is underway. He also told me that the sentiment engine notices a lot of “going out” kinds of messages on Friday afternoon and then notices a lot of “hungover” messages on Saturday morning. He’s not sure where that research will lead. We talked about how sentiment analysis might lead to a new kind of news display in Facebook. Knowing whether a story is positive or negative would let Facebook pick a good selection of both kinds of news, or maybe even let you choose whether you want to see only “happy” news.

Sentiment Targeted Facebook Ads?

While Facebook’s advertising solutions already let marketers reach Facebook users in a profile-targeted way (age, sex, location, relationship status, interests, education), imagine the possibilities if Facebook let marketers target users according to their mood in real time.

• Users in a celebratory mood could be shown ads for champagne or fine restaurants.
• Those in a sad mood about the stock market could be shown ads for financial services firms (or Cash4Gold).

In brief, mood targeting could improve Facebook’s advertising performance in a number of verticals, from discretionary spending categories like cars and dining to traditional CPA categories like finance and dating.

Below: What might the advertiser mood targeting dashboard look like?

The Privacy Angle

“With great power comes great responsibility,” and changing the user experience based on inferred mood in real time certainly has some spook potential. It’s a major challenge, but Facebook has a lot of experience navigating complicated privacy questions.

Facebook’s Director of Monetization Tim Kendall told us recently, “We’ve done pretty well with privacy on [Social Ads] because we stick to what the user provides to us.” Applying that framework to a mood targeting system may be more complex – determining a user’s mood would likely often require inference, unlike profile targeting done today against information explicitly declared by users.

Conclusion

Given the potential for sentiment-targeted ads to substantially improve social network advertising performance, Facebook will rest assured thoroughly examine building such a system as it develops its sentiment engine technology further. Whether Facebook’s “mood detector” ever makes it to the live site – either in News Feed or advertisement form – is anybody’s guess.