Stance Detection with Collaborative Role-Infused LLM-Based Agents

arXiv:2310.10467v2 Announce Type: replace
Abstract: Stance detection automatically detects the stance in a text towards a target, vital for content analysis in web and social media research. Despite their promising capabilities, LLMs encounter challenges when directly applied to stance detection. First, stance detection demands multi-aspect knowledge, from deciphering event-related terminologies to understanding the expression styles in social media platforms. Second, stance detection requires advanced reasoning to infer authors' implicit viewpoints, as stance are often subtly embedded rather than overtly stated …

abstract agents analysis arxiv capabilities challenges collaborative cs.ai cs.cl detection event knowledge llm llms media research role social social media text type understanding vital web