DeepAI AI Chat
Log In Sign Up

Misinformation Detection on YouTube Using Video Captions

by   Raj Jagtap, et al.

Millions of people use platforms such as YouTube, Facebook, Twitter, and other mass media. Due to the accessibility of these platforms, they are often used to establish a narrative, conduct propaganda, and disseminate misinformation. This work proposes an approach that uses state-of-the-art NLP techniques to extract features from video captions (subtitles). To evaluate our approach, we utilize a publicly accessible and labeled dataset for classifying videos as misinformation or not. The motivation behind exploring video captions stems from our analysis of videos metadata. Attributes such as the number of views, likes, dislikes, and comments are ineffective as videos are hard to differentiate using this information. Using caption dataset, the proposed models can classify videos among three classes (Misinformation, Debunking Misinformation, and Neutral) with 0.85 to 0.90 F1-score. To emphasize the relevance of the misinformation class, we re-formulate our classification problem as a two-class classification - Misinformation vs. others (Debunking Misinformation and Neutral). In our experiments, the proposed models can classify videos with 0.92 to 0.95 F1-score and 0.78 to 0.90 AUC ROC.


page 4

page 5


Clickbait Detection in YouTube Videos

YouTube videos often include captivating descriptions and intriguing thu...

Approach for Video Classification with Multi-label on YouTube-8M Dataset

Video traffic is increasing at a considerable rate due to the spread of ...

The MeLa BitChute Dataset

In this paper we present a near-complete dataset of over 3M videos from ...

Interactive Variance Attention based Online Spoiler Detection for Time-Sync Comments

Nowadays, time-sync comment (TSC), a new form of interactive comments, h...

Deepfake Detection Scheme Based on Vision Transformer and Distillation

Deepfake is the manipulated video made with a generative deep learning t...

Efficient video integrity analysis through container characterization

Most video forensic techniques look for traces within the data stream th...