My Words Imply Your Opinion: Reader Agent-Based Propagation Enhancement for Personalized Implicit Emotion Analysis

2024-12-10

arXiv.org

AI Summary

Existing implicit sentiment analysis primarily focuses on unidirectional author expression, neglecting the influence of readers’ subjective feedback on sentiment interpretation, thereby limiting personalized modeling. This paper proposes Personalized Implicit Emotion Analysis (PIEA), a novel paradigm that explicitly models bidirectional emotional interaction between authors and readers. Methodologically: (1) we design a large-language-model-driven reader agent simulation mechanism; (2) we construct a role-aware multi-view graph neural network to explicitly capture implicit sentiment propagation; and (3) we release the first bilingual (Chinese–English) PIEA benchmark dataset featuring fine-grained user metadata. Our RAPPIE model achieves significant improvements over state-of-the-art methods on this benchmark, empirically validating both the effectiveness and necessity of incorporating the reader’s perspective for enhancing personalized implicit sentiment modeling.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Emotional Intelligence
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The subtlety of emotional expressions makes implicit emotion analysis (IEA) particularly sensitive to user-specific characteristics. Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback. In this paper, we introduce Personalized IEA (PIEA) and present the RAPPIE model, which addresses subjective variability by incorporating reader feedback. In particular, (1) we create reader agents based on large language models to simulate reader feedback, overcoming the issue of ``spiral of silence effect'' and data incompleteness of real reader reaction. (2) We develop a role-aware multi-view graph learning to model the emotion interactive propagation process in scenarios with sparse reader information. (3) We construct two new PIEA datasets covering English and Chinese social media with detailed user metadata, addressing the text-centric limitation of existing datasets. Extensive experiments show that RAPPIE significantly outperforms state-of-the-art baselines, demonstrating the value of incorporating reader feedback in PIEA.

Problem

• Enhances implicit emotion analysis with reader feedback.
• Simulates reader reactions using large language models.
• Creates datasets addressing text-centric limitations in emotion analysis.

Innovation

• Reader agents simulate feedback
• Role-aware graph models emotion
• New datasets enhance analysis