Persona-E²: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events

Jul 2, 2026·
Yuqin Yang
,
Haowu Zhou
,
Haoran Tu
,
Zhiwen Hui
,
Shiqi Yan
,
HaoYang Li
,
Dong She
,
Xianrong Yao
,
Yang Gao
,
Zhanpeng Jin
Persona-E² data collection, personality-grounded annotation, and evaluation framework. Figure 1 from the paper.
Abstract
Persona-E² is a human-grounded dataset of personality-shaped emotional responses to textual events across news, social media, and life narratives. Annotations combine MBTI and Big Five traits with reader appraisals, enabling evaluation of emotional diversity and personality-conditioned LLM reasoning. Experiments show that personality information improves appraisal prediction, while current models still struggle to reproduce human emotional variation.
Type
Publication
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026, Main Conference)

Persona-E2 dataset composition across news, social media, and life experience from Figure 2.

ACL Main Conference Dataset Emotion Personality Natural Language Processing