EmoPerso: Enhancing Personality Detection with Self-Supervised Emotion-Aware Modelling
This work addresses the problem of personality detection for social media analysis, offering an incremental improvement by integrating emotion-aware modelling.
The paper tackles personality detection from text by addressing the reliance on large annotated datasets and the oversight of emotion-personality interactions, proposing a self-supervised framework that improves performance over state-of-the-art models on benchmark datasets.
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.