Facebook News Feed now favors articles users spend a long time reading
Featured
Facebook has made yet another tweak to its News Feed algorithm as part of its ongoing effort to keep users interested in the content they see on the site.
In a previous update earlier this year, Facebook focused on two particular signals for News Feed worthiness: The probability that users want to see a particular story at the top of their feed, and the probability they'll like, share or comment on it.
But as new Facebook research has found out, there are stories people don't like or comment on that they still want to see, such as a sad post from a friend, a story about a natural disaster, or the death of a music icon (RIP, Prince).
That said, Facebook is now taking into account how much time users spend reading a post within News Feed. The algorithm will attempt to predict how long someone spends looking at an article in the Facebook mobile browser or an Instant Article that was clicked on from News Feed.
From Facebook's blog post:
This update to ranking will take into account how likely you are to click on an article and then spend time reading it. We will not be counting loading time towards this -- we will be taking into account time spent reading and watching once the content has fully loaded. We will also be looking at the time spent within a threshold so as not to accidentally treat longer articles preferentially.
With this change, we can better understand which articles might be interesting to you based on how long you and others read them, so you'll be more likely to see stories you're interested in reading. This change only factors in the time people spend reading an article regardless of whether that time is spent reading an Instant Article or an article in the mobile web browser.
Facebook is also going for more diversity among the publishers it shows users in News Feed. The social network has realized people tend to get annoyed when they see multiple posts in a row from the same publisher, so now it will try to spread the love between different pages a user has liked.
More: