acm-header
Sign In

Communications of the ACM

ACM TechNews

Algorithm Amplifies Trustworthy News Content on Social Media Without Shielding Bias


A woman checks her social media.

The researchers say that platforms would easily be able to include audience diversity into their own recommendation algorithms because diversity measures can be derived from engagement data, and platforms already log this type of data whenever users click

Credit: University of South Florida Newsroom

Researchers at the University of South Florida (USF), Indiana University (IU), and Dartmouth College have developed a method for amplifying trustworthy news on social media.

The researchers analyzed content amplified on newsfeeds by recommendation algorithms, targeting a source's reliability score and the political variegation of their audience.

They devised an algorithm using data on Web traffic and the self-reported partisanship of 6,890 persons who reflect the sexual, racial, and political diversity of the U.S., and reviewed the reliability scores of 3,765 news sources based on the NewGuard Reliability Index.

They found that adding a news audience's partisan diversity to the algorithm can boost the reliability of recommended sources while still supplying relevant recommendations, irrespective of partisanship.

IU's Filippo Menczer said, "This is especially welcome news for social media platforms, especially since they have been reluctant of introducing changes to their algorithms for fear of criticism about partisan bias."

From University of South Florida Newsroom
View Full Article

 

Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


 

No entries found