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.

The last several years have seen a massive increase in the quantity and influence of disinformation being spread online. Various approaches have been developed to target the process at different stages from identifying sources to tracking distribution in social media to providing follow up debunks to people who have encountered the disinformation. One common conclusion in each of these approaches is that disinformation is too nuanced and subjective a topic for fully automated solutions to work but the quantity of data to process and cross-reference is too high for humans to handle unassisted. Ultimately, the problem calls for a hybrid approach of human experts with technological assistance. In this paper we will demonstrate the application of certain state-of-the-art NLP techniques in assisting expert debunkers and fact checkers as well as the role of these NLP algorithms within a more holistic approach to analyzing and countering the spread of disinformation. We will present a multilingual corpus of disinformation and debunks which contains text, concept tags, images and videos as well as various methods for searching and leveraging the content.