Which Factors Impact Engagement on News Articles on Facebook?
This work addresses the need for newspapers to optimize Facebook engagement for better news-feed ranking, though it is incremental as it applies existing methods to analyze social media data.
The paper tackled the problem of understanding which factors impact engagement on news articles on Facebook, finding that delay between event and post release, time of day, and post format influence reaction volume, with the news-aggregator tool enabling control for news-event and newspaper effects.
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.