Misinformation Detection in Social Media Video Posts
Abstract
With the growing adoption of short-form video by social media platforms, reducing the spread of misinformation through video posts has become a critical challenge for social media providers. In this paper, we develop methods to detect misinformation in social media posts, exploiting modalities such as video and text. Due to the lack of large-scale public data for misinformation detection in multi-modal datasets, we collect 160,000 video posts from Twitter, and leverage self-supervised learning to learn expressive representations of joint visual and textual data. In this work, we propose two new methods for detecting semantic inconsistencies within short-form social media video posts, based on contrastive learning and masked language modeling. We demonstrate that our new approaches outperform current state-of-the-art methods on both artificial data generated by random-swapping of positive samples and in the wild on a new manually-labeled test set for semantic misinformation.
Cite
@article{arxiv.2202.07706,
title = {Misinformation Detection in Social Media Video Posts},
author = {Kehan Wang and David Chan and Seth Z. Zhao and John Canny and Avideh Zakhor},
journal= {arXiv preprint arXiv:2202.07706},
year = {2022}
}
Comments
We discovered an error in our dataset construction where retweets were not properly filtered. This resulted in test data leakage in training data, and the results reported are affected