Facebook optimizes anti-clickbait algorithm to further weed out low-quality content

Datetime:2016-08-23 03:14:47          Topic: Algorithm           Share

Facebook is once again modifying the algorithm that controls its News Feed in an effort to further reduce the number of clickbait stories that show up in users’ feeds.

Alex Peysakhovich, Research Scientist and Kristin Hendrix, User Experience Researcher at Facebook, describe clickbait stories as those with headlines that intentionally leave out crucial information or otherwise attempt to mislead readers and get them to click their story.

Examples of such stories might use headlines like “When She Looked Under Her Couch Cushions And Saw THIS… I Was SHOCKED!”; “He Put Garlic In His Shoes Before Going To Bed And What Happens Next Is Hard To Believe”; or “The Dog Barked At The Deliveryman And His Reaction Was Priceless.”

Peysakhovich and Hendrix pointed to an earlier update to combat clickbaiting that weeded out stories in which users clicked then quickly returned to their feed but that only helped so much. The new update uses a system that identifies phrases commonly used in clickbait headlines to categorize them accordingly.

The system is also able to tag domains or Facebook Pages that consistently post clickbait headlines and will make sure that their content appears lower in the News Feed. What’s more, the anti-clickbait system will get smarter over time. If a publication cleans up its act, for example, their posts will stop being ranked as low.

With any luck, this change will serve as a catalyst for change and convince at least some sites to reconsider how they attract traffic.

Image courtesy durantelallera, Shutterstock





About List