PRISM of Opinions: A Persona-Reasoned Multimodal Framework for User-centric Conversational Stance Detection

TL;DR

This paper introduces PRISM, a novel multimodal framework that incorporates user personas and conversational context to improve stance detection on social media, addressing previous limitations of pseudo-multimodality and user homogeneity.

Contribution

It presents U-MStance, a new user-centric multimodal stance detection dataset, and PRISM, a model that leverages user personas and multimodal reasoning for more accurate stance analysis.

Findings

PRISM outperforms strong baselines on U-MStance.

User personas enhance stance detection accuracy.

Multimodal reasoning improves contextual understanding.

Abstract

The rapid proliferation of multimodal social media content has driven research in Multimodal Conversational Stance Detection (MCSD), which aims to interpret users' attitudes toward specific targets within complex discussions. However, existing studies remain limited by: **1) pseudo-multimodality**, where visual cues appear only in source posts while comments are treated as text-only, misaligning with real-world multimodal interactions; and **2) user homogeneity**, where diverse users are treated uniformly, neglecting personal traits that shape stance expression. To address these issues, we introduce **U-MStance**, the first user-centric MCSD dataset, containing over 40k annotated comments across six real-world targets. We further propose **PRISM**, a **P**ersona-**R**easoned mult**I**modal **S**tance **M**odel for MCSD. PRISM first derives longitudinal user personas from historical posts and comments to capture individual traits, then aligns textual and visual cues within conversational context via Chain-of-Thought to bridge semantic and pragmatic gaps across modalities. Finally, a mutual task reinforcement mechanism is employed to jointly optimize stance detection and stance-aware response generation for bidirectional knowledge transfer. Experiments on U-MStance demonstrate that PRISM yields significant gains over strong baselines, underscoring the effectiveness of user-centric and context-grounded multimodal reasoning for realistic stance understanding.