Marc Faddoul

Marc Faddoul, Guillaume Chaslot, Hany Farid

Conspiracy theories have flourished on social media, raising concerns that such content is fueling the spread of disinformation, supporting extremist ideologies, and in some cases, leading to violence. Under increased scrutiny and pressure from legislators and the public, YouTube announced efforts to change their recommendation algorithms so that the most egregious conspiracy videos are demoted and demonetized. To verify this claim, we have developed a classifier for automatically determining if a video is conspiratorial (e.g., the moon landing was faked, the pyramids of Giza were built by aliens, end of the world prophecies, etc.). We coupled this classifier with an emulation of YouTube's watch-next algorithm on more than a thousand popular informational channels to obtain a year-long picture of the videos actively promoted by YouTube. We also obtained trends of the so-called filter-bubble effect for conspiracy theories.

Marc Faddoul

Social media is increasingly being used as a news-platform. To reach their intended audience, newspapers need for their articles to be well ranked by Facebook's news-feed algorithm. The number of likes, shares and other reactions determine the lead scoring criteria. This paper will try to assess how the reaction volume is impacted by the following criteria: (1) Delay between event and post release; (2) Time of the day the post is published; and (3) Post format: video, photo or text. To isolate the effect of the publication time and post format on a post, we need to control for the news-event and the publishing newspaper. For that end, a news-aggregator is designed and implemented, to group together posts that relate to the same news-event. This tool gave some spin-off results, allowing the ability to map newspapers by similarity and to detect some topic omissions.