Facebook has been conducting user surveys to fine-tune News Feed for quite some time, and the social network provided more details on those efforts in a Newsroom post.
Software engineer Sami Tas and data scientist Ta Virot Chiraphadhanakul wrote about the surveys:
As part of our ongoing effort to improve News Feed, we ask thousands of people every day to rate their experience and tell us how we can improve what they see when they check Facebook. People also take story surveys where they see two stories that could be in their News Feed and answer which they’d most want to see. We compare their answer to the order we would have put these stories in their News Feed. If the story picked is the one News Feed would have shown higher up, that’s a good sign that things are working well. If the story picked is the one we would have put lower down, this highlights an area for improvement.
Tas and Chiraphadhanakul also discussed how the social network tries to determine which viral posts are interesting to Facebook users and which they would rather not see:
We survey tens of thousands of people every day, and for the story surveys, we ask them if they prefer a particular viral post to another post. With this update, if a significant amount of people tell us they would prefer to see other posts more than that particular viral post, we’ll take that into account when ranking, so that viral post might show up lower in people’s feeds in the future, since it might not actually be interesting to people. With the hoaxes example, if the majority of people taking the survey say they would rather see another story in their feed than the viral hoax story, then we’ll infer the story might not be as interesting, and show the viral story lower down in people’s feeds in the future.
As for the potential impact on pages, they wrote:
As viral posts are typically anomalies, and not an important part of distribution for pages, we don’t think this change will impact your page’s distribution.
Readers: Have you ever taken one of Facebook’s News Feed surveys?
No comments:
Post a Comment