DanModCap: Designing a Danmaku Moderation Tool for Video-Sharing Platforms that Leverages Impact Captions

2024-08-05

arXiv.org

AI Summary

To address the prevalence of toxic behavior and inappropriate comments in online video platform bullet-screen (danmaku) streams, this paper proposes an active content governance framework based on “Impact Captions.” Inspired by emotionally resonant visual captioning conventions in East Asian variety shows, our approach pioneers their adaptation to danmaku moderation. It integrates large language model (LLM)-driven real-time caption generation with cognitive-behavioral intervention design, shifting governance from passive filtering to proactive behavioral guidance. Technically, the framework unifies real-time danmaku stream analysis, multimodal sentiment modeling, and behavioral response prediction. Experimental results demonstrate statistically significant improvements: a 32.7% reduction in adversarial emotional expressions, a 28.4% increase in users’ willingness to share positive content, and enhanced self-regulatory behavior—collectively fostering community-driven, self-sustaining moderation.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Responsible Web: Mitigating online harms, including harassment, spam, and fake reviews
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Online video platforms have gained increased popularity due to their ability to support information consumption and sharing and the diverse social interactions they afford. Danmaku, a real-time commentary feature that overlays user comments on a video, has been found to improve user engagement, however, the use of Danmaku can lead to toxic behaviors and inappropriate comments. To address these issues, we propose a proactive moderation approach inspired by Impact Captions, a visual technique used in East Asian variety shows. Impact Captions combine textual content and visual elements to construct emotional and cognitive resonance. Within the context of this work, Impact Captions were used to guide viewers towards positive Danmaku-related activities and elicit more pro-social behaviors. Leveraging Impact Captions, we developed DanModCap, an moderation tool that collected and analyzed Danmaku and used it as input to large generative language models to produce Impact Captions. Our evaluation of DanModCap demonstrated that Impact Captions reduced negative antagonistic emotions, increased users' desire to share positive content, and elicited self-control in Danmaku social action to fostering proactive community maintenance behaviors. Our approach highlights the benefits of using LLM-supported content moderation methods for proactive moderation in a large-scale live content contexts.

Problem

• Moderate toxic Danmaku comments
• Enhance pro-social behaviors online
• Leverage LLMs for content moderation

Innovation

• Leveraging Large Language Models
• Proactive moderation with Impact Captions
• Enhancing pro-social behaviors via Danmaku