Predicting the Leading Political Ideology of YouTube Channels Using Acoustic, Textual, and Metadata Information
This addresses the problem of political bias detection for researchers and media analysts by introducing a multimodal approach, though it is incremental as it builds on existing text-based methods.
The paper tackled predicting the political ideology of YouTube news channels by using acoustic, textual, and metadata information, resulting in a 6% absolute improvement in bias detection when including acoustic signals over text and metadata alone.
We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.