Current emotion analysis in social media is predominantly author-centric, failing to capture the subjective nature of emotional responses across diverse readers. This paradigm overlooks the crucial link between individual perception, implicit propagation intent, propagation behavior, and the underlying social network. To bridge this gap, we introduce EmoIntenNet, a novel bilingual (English and Chinese) large-scale benchmark that uniquely integrates six critical dimensions for social perception: author-created content, actual readers’ emotional feedback (derived from their comments), implicit propagation intent, explicit propagation behavior, user attributes, and the social relationship graph. This benchmark advances the shift towards more granular, reader-centric analysis, where different readers’ emotional responses to the same content are grounded in their actual social interactions rather than simulated annotations. By annotating implicit emotions from reader comments and synchronously capturing implicit multi-label propagation intents, EmoIntenNet provides a unique resource to model the intrinsic triadic coupling among implicit emotion, implicit intent, and explicit behavior, grounded in social context. We establish a comprehensive evaluation protocol, testing state-of-the-art methods, including large language models (LLMs) with advanced reasoning enhancement. Our findings reveal significant shortcomings in existing approaches when handling this multifaceted, user-aware task. EmoIntenNet offers a foundational resource and clear direction for future research in socially-intelligent NLP, pushing models towards a more unified understanding of emotion on social media.

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.