Personality detection from text is commonly performed by analysing users' social media posts. However, existing methods heavily rely on large-scale annotated datasets, making it challenging to obtain high-quality personality labels. Moreover, most studies treat emotion and personality as independent variables, overlooking their interactions. In this paper, we propose a novel self-supervised framework, EmoPerso, which improves personality detection through emotion-aware modelling. EmoPerso first leverages generative mechanisms for synthetic data augmentation and rich representation learning. It then extracts pseudo-labeled emotion features and jointly optimizes them with personality prediction via multi-task learning. A cross-attention module is employed to capture fine-grained interactions between personality traits and the inferred emotional representations. To further refine relational reasoning, EmoPerso adopts a self-taught strategy to enhance the model's reasoning capabilities iteratively. Extensive experiments on two benchmark datasets demonstrate that EmoPerso surpasses state-of-the-art models. The source code is available at https://github.com/slz0925/EmoPerso.
@article{arxiv.2509.02450,
title = {EmoPerso: Enhancing Personality Detection with Self-Supervised Emotion-Aware Modelling},
author = {Lingzhi Shen and Xiaohao Cai and Yunfei Long and Imran Razzak and Guanming Chen and Shoaib Jameel},
journal= {arXiv preprint arXiv:2509.02450},
year = {2025}
}