Community Conversation
Community conversation analysis focuses on understanding the dynamics and nuances of human interaction within groups, aiming to extract meaningful information about social norms, emotions, and intentions. Current research employs various deep learning models, including transformer networks and graph neural networks, to analyze multimodal data (text, audio, video) and predict aspects like emotion, empathy, and the presence of manipulation or toxicity. This field is significant for advancing human-computer interaction, improving social robot design, and developing tools for community needs assessment and conflict resolution in diverse settings.
Papers
CausalDialogue: Modeling Utterance-level Causality in Conversations
Yi-Lin Tuan, Alon Albalak, Wenda Xu, Michael Saxon, Connor Pryor, Lise Getoor, William Yang Wang
Contrastive Learning Reduces Hallucination in Conversations
Weiwei Sun, Zhengliang Shi, Shen Gao, Pengjie Ren, Maarten de Rijke, Zhaochun Ren