Using Topic Modeling and Adversarial Neural Networks for Fake News Video Detection

doi:10.1145/3459637.3482212

Paper

Using Topic Modeling and Adversarial Neural Networks for Fake News Video Detection

Published Oct 26, 2021 · H. Choi, Youngjoong Ko

Proceedings of the 30th ACM International Conference on Information & Knowledge Management

30

Citations

9

Influential Citations

Full text

Abstract

Fake news videos are being actively produced and uploaded on YouTube to attract public attention. In this paper,we propose a topic-agnostic fake news video detection model based on adversarial learning and topic modeling. The proposed model estimates the topic distribution of a video using its title/description and comments by topic modeling and tries to identify the differences in stance by the topic distribution difference between title/description and comments. Then, it constructs an adversarial neural network to extract topic-agnostic features effectively. The proposed model can effectively detect topic changes for stance analysis and easily shift among various topics. In this study, it achieves an F1-score 2.68% point greater than previous models in fake news video detection.

Study Snapshot

The proposed topic-agnostic fake news video detection model using adversarial learning and topic modeling achieves a 2.68% higher F1-score compared to previous models, effectively detecting topic changes and shifting among various topics.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Using Topic Modeling and Adversarial Neural Networks for Fake News Video Detection

References

Citations