Mining the User’s Personality With an Attention-Based Label Prompt Method
Liping Chen, Yilin Wu, Qiudan Li, Yuxuan Song, Chenyu Yuan, Daniel Dajun Zeng · IEEE Intelligent Systems · 2023
Identifying personality traits from online posts is becoming a hot research topic and often plays an essential role in behavior analysis and recommender systems. Previous studies have adopted deep neural networks or pretrained language models to mine semantic information without considering the prompting role of personality labels and the connection between writing style and personality traits. This paper proposes an attention-based label-prompt method (ABLPM) to address the above challenges. The ABLPM utilizes label-prompt semantic learning to generate personality representations while integrating writing style into text semantics. Then, the style-enhanced attention mechanism further constructs the deep dynamic interaction among the personality label, text semantics, and writing style. Finally, multiple loss functions optimize the distribution of the generated personality representations. The experimental results with the MyPersonality and topic-oriented social media comment datasets demonstrate the efficacy of the proposed method.