Understanding Toxic Interaction Across User and Video Clusters in Social Video Platforms
Qiao Wang, Liang Liu, Mitsuo Yoshida

TL;DR
This study analyzes toxic interactions on Bilibili by clustering users and videos based on interaction patterns and content, revealing community-specific behaviors and exposure risks.
Contribution
It introduces a clustering-based approach that combines structural interaction data with content features to identify stable user and video groups in social video platforms.
Findings
Higher exposure groups tend to have more toxic expressions.
User clusters with longer messages and more comments show lower toxicity.
Interaction style varies significantly across user clusters, but less so across video clusters.
Abstract
Social video platforms shape how people access information, while recommendation systems can narrow exposure and increase the risk of toxic interaction. Previous research has often examined text or users in isolation, overlooking the structural context in which such toxic interactions occur. Without considering who interacts with whom and around what content, it is difficult to explain why negative expressions cluster within particular communities. To address this issue, this study focuses on the Chinese social video platform Bilibili, incorporating video-level information as the environment for user expression, modeling users and videos in an interaction matrix. After normalization and dimensionality reduction, we perform separate clustering on both sides of the video-user interaction matrix with K-means. Cluster assignments facilitate comparisons of user behavior, including message…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
