arXiv cs.CY· Claire Wonjeong Jo, Miki Weso{\l}owska, Magdalena Wojcieszak·· 12 小时前AI 评分31
有害 YouTube 视频检测：在线危害分类体系与 MLLMs 作为替代标注者
Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators
AI 导读
研究提出将在线危害分为 Information、Hate and harassment、Addictive、Clickbait、Sexual、Physical 六类的多模态分类体系，并系统测试 MLLMs 作为有害视频替代标注者。
正文 · 原文
Abstract:Video platforms, used by billions globally, are criticized for exposing users to harmful content. Yet, detecting online harm remains challenging due to inconsistent approaches to what constitutes harm and limitations of human annotation. We address both challenges. Theoretically, we integrate and expand existing taxonomies and platform guidelines to multimodal contexts and develop a comprehensive taxonomy for online harm. We categorize online harm on video platforms into six content-based categories: Information, Hate and harassment, Addictive, Clickbait, Sexual, and Physical harms. Methodologically, we propose and systematically test multimodal large language models (MLLMs) as alternative annotators of harmful videos. We curate a dataset of 19,422 potentially harmful YouTube videos and annotate them using GPT-4-Turbo, non-trained crowdworkers, and trained annotators. We discuss the potential applications of MLLMs in platform content moderation and social science research, particularly in contexts where they perform comparably to human annotators in binary and multi-label classification tasks.
| Subjects: | Multimedia (cs.MM); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY) |
| Cite as: | arXiv:2411.05854 [cs.MM] |
| (or arXiv:2411.05854v2 [cs.MM] for this version) | |
| https://doi.org/10.48550/arXiv.2411.05854 arXiv-issued DOI via DataCite |
Submission history
From: Claire Wonjeong Jo [view email]
[v1]
Wed, 6 Nov 2024 23:48:30 UTC (1,073 KB)
[v2]
Wed, 14 Oct 2026 20:10:11 UTC (720 KB)
来源：arXiv cs.CY · arxiv.org