Predicting the Factuality of Reporting of News Media Using Observations About User Attention in Their YouTube Channels

TL;DR

This paper introduces a new method for assessing news media factuality by analyzing user attention patterns on YouTube, leveraging temporal engagement data to improve accuracy over traditional text-based methods.

Contribution

It presents a novel framework and dataset for predicting news factuality using user attention dynamics on YouTube channels, outperforming existing textual approaches.

Findings

Attention-based features improve factuality prediction accuracy.

The dataset includes observations from 489 news media channels.

The approach demonstrates significant gains over state-of-the-art text models.

Abstract

We propose a novel framework for predicting the factuality of reporting of news media outlets by studying the user attention cycles in their YouTube channels. In particular, we design a rich set of features derived from the temporal evolution of the number of views, likes, dislikes, and comments for a video, which we then aggregate to the channel level. We develop and release a dataset for the task, containing observations of user attention on YouTube channels for 489 news media. Our experiments demonstrate both complementarity and sizable improvements over state-of-the-art textual representations.