Persona-E$^2$: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events
2026-04-10 • Computation and Language
Computation and LanguageArtificial IntelligenceHuman-Computer Interaction
AI summaryⓘ
The authors point out that most emotion-detecting computer programs only consider how a writer feels, ignoring how different readers might feel differently based on their personalities. To fix this, they created a new dataset called Persona-E² that links people's personalities (using MBTI and Big Five models) to their emotional reactions to various texts like news and social media posts. They tested large language models and found these models have trouble understanding these personalized emotional shifts, especially in social media. The authors also show that including personality information helps models better predict emotions and reduces reliance on simple stereotypes.
affective computingemotion appraisalMBTIBig Five personality traitslarge language modelspersonality illusiondatasetsocial mediaemotional variationpersona-based modeling
Authors
Yuqin Yang, Haowu Zhou, Haoran Tu, Zhiwen Hui, Shiqi Yan, HaoYang Li, Dong She, Xianrong Yao, Yang Gao, Zhanpeng Jin
Abstract
Most affective computing research treats emotion as a static property of text, focusing on the writer's sentiment while overlooking the reader's perspective. This approach ignores how individual personalities lead to diverse emotional appraisals of the same event. Although role-playing Large Language Models (LLMs) attempt to simulate such nuanced reactions, they often suffer from "personality illusion'' -- relying on surface-level stereotypes rather than authentic cognitive logic. A critical bottleneck is the absence of ground-truth human data to link personality traits to emotional shifts. To bridge the gap, we introduce Persona-E$^2$ (Persona-Event2Emotion), a large-scale dataset grounded in annotated MBTI and Big Five traits to capture reader-based emotional variations across news, social media, and life narratives. Extensive experiments reveal that state-of-the-art LLMs struggle to capture precise appraisal shifts, particularly in social media domains. Crucially, we find that personality information significantly improves comprehension, with the Big Five traits alleviating "personality illusion.'