Recommender Systems and Misinformation: The Problem or the Solution?

Fernandez, Miriam and Bellogin, Alejandro (2020). Recommender Systems and Misinformation: The Problem or the Solution? In: OHARS Workshop. 14th ACM Conference on Recommender Systems, 22-26 Sep 2020, [Online].

Abstract

Recommender Systems have been pointed as one of the major culprits of misinformation spreading in the digital sphere. These systems have recently gone under heavy criticism for promoting the creation of filter bubbles, lowering the diversity of information users are exposed to and the social contacts they create. This influences the dynamics of social news sharing, and particularly the ways misinformation initiates and propagates. However, while Recommender Systems have been accused of fuelling the spread of misinformation, it is still unclear which particular types of recommender algorithms are more prone to recommend misinforming news, and if, and how, existing recommendation algorithms and evaluation metrics, can be modified or adapted to mitigate the misinformation spreading effect. In this position paper, we describe some of the key challenges behind assessing and measuring the effect of existing recommendation algorithms on the recommendation of misinforming articles and how such algorithms could be adapted, modified, and evaluated to counter this effect based on existing social science and psychology research.

Viewing alternatives

Download history

Item Actions

Export

About

Recommendations