A Chinese Multimodal Social Video Dataset for Controversy Detection

Tianjiao Xu, Aoxuan Chen, Yuxi Zhao, Jinfei Gao, Tian Gan

Abstract: Social video platforms have emerged as significant channels for information dissemination, facilitating lively public discussions that often give rise to controversies. However, existing approaches to controversy detection primarily focus on textual features, which raises three key concerns: it underutilizes the potential of visual information available on social media platforms; it is ineffective when faced with incomplete or absent textual information; and the existing datasets fail to adequately address the need for comprehensive multimodal resources on social media platforms. To address these challenges, we construct a large-scale Multimodal Controversial Dataset (MMCD) in Chinese. Additionally, we propose a novel framework named Multi-view Controversy Detection (MVCD) to effectively model controversies from multiple perspectives. Through extensive experiments using state-of-the-art models on the MMCD, we demonstrate MVCD's effectiveness and potential impact.

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Engagement] Emotional and Social Signals, [Content] Multimodal Fusion, [Content] Media Interpretation

Relevance To Conference: We introduce a large-scale Chinese Multimodal Controversial Dataset (MMCD), providing a valuable resource for studying controversies. In addition, we propose a novel framework called Multi-view Controversy Detection (MVCD), which can effectively model multimodal video content and the interaction between social contexts. To the best of our knowledge, this is the first investigation of its kind. The work aligns precisely with the scope of ACM MULTIMEDIA, which focuses on multimedia and related application fields, calling for research papers presenting novel theoretical and algorithmic solutions to address problems in these domains.

Submission Number: 5161