Let’s back up. One thing I like about Facebook is that it’s never stagnant—there are always tweaks and experiments and changes, all with a view toward improving some part of the Facebook experience. Sometimes that’s for users, sometimes for advertisers and brands, sometimes it’s purely to benefit Facebook. I think that’s important, and what any vibrant business needs to be doing today—constantly changing and striving to improve. Of course, users complain incessantly about changes any time they happen, but that’s silly. In today’s world, change is inevitable. Whether it’s to the Facebook platform or anything else.
So what’s the deal with the News Feed? Facebook continues to experiment there as well, with a view toward better adapting to user preferences. In recent months, Facebook has been conducting some News Feed tests, in which some users are shown the top posts in their feeds, alongside one another, asking them to pick which post they’d prefer to read. The result? The algorithm’s rankings are attempting to collect data that will allow it to correspond more accurately to users’ preferences. Sometimes. And when the results don’t match up, that points to an area that needs work.
Sorting Algorithms and Feed Quality Panels
Tom Alison is director of engineering for the Facebook News Feed; he’s in charge of the humans who are in charge of the algorithm. “When you study computer science, one of the first algorithms you learn is a sorting algorithm,” Alison says, “Human beings know how to do this. We just kind of do it in our heads.”
“Let’s say I ask you to pick the winner of a future basketball game, the Bulls vs. the Lakers,” Alison begins. “Random guessing is fine when you’ve got nothing to lose,” Alison says, “But let’s say there was a lot of money riding on my basketball predictions, and I was making them millions of times a day. I’d need a more systematic approach. You’re probably going to start by looking at historical data. Yet no matter how meticulously you construct an algorithm, there are always going to be data to which you aren’t privy: the coaches’ game plans, how Derrick Rose’s knee is feeling that day, whether the ball is properly inflated. In short, the game isn’t played by data. It’s played by people. And people are too complex for any algorithm to model.” Well, yes.
Adam Mosseri, Facebook’s director of product for the News Feed, is Alison’s less technical counterpart, who started focusing on the News Feed in late 2013. One of the first things Mosseri did was to create “feed quality panel” comprised of users—a focus group, if you will. The first feed quality panel took place in Knoxville in the summer of 2014, and the participants were paid to provide continual and detailed feedback on what they saw in their News Feeds. Mosseri and his team studied their behavior and also asked them myriad questions, attempting to understand as fully as possible not only what they liked (or didn’t like) about a given post, but also why they liked it, and/or what they might have preferred to see instead.
The company has grown increasingly aware that no single source of data can tell it everything. It has responded by developing a sort of checks-and-balances system in which every News Feed tweak must undergo a battery of tests among different types of audiences, and be judged on a variety of different metrics.
Facebook’s News Feed ranking team believes the change in its approach is paying off. According to Lauren Scissors, the user experience researcher who helps to oversee the feed quality panel, “As we continue to improve News Feed based on what people tell us, we are seeing that we’re getting better at ranking people’s News Feeds; our ranking is getting closer to how people would rank stories in their feeds themselves.”
So who controls your Facebook News Feed? You do. Or people and focus groups assembled because they are supposed to be representatives of you—designed to serve up a better user experience for all. What do you think? Have you seen Facebook’s News Feed experiments in your Feed? Do you notice you’re seeing things that are better suited to your preferences over the course of the last year? I notice that I see fewer things that annoy me—what about you?
Additional Resources on this Topic: