Unveiling the Hidden Interactions Among Features: A Heterogeneous Graph Approach for Personality Prediction

Identifying personalities accurately helps merchants and management departments understand user needs in detail and improve the quality of service and decision-making efficiency. Existing research on text-based personality prediction mainly uses deep neural networks or pretrained language models to mine deep semantics, ignoring the dynamic interactions among personality features. This paper presents a novel personality prediction method that simultaneously taps into the capability of graph neural networks to model the deep interactions among features and that of pretrained language models to learn latent semantics with a hierarchical aggregation mechanism. Specifically, the proposed model leverages self-attention to capture the interaction relationships among POS tags, entities, personality tags, etc., and considers the labels′ cooccurrence patterns. The efficacy of the proposed model is evaluated on the myPersonality and PANDORA datasets. This research contributes to the personality prediction literature from the perspective of a multigranular personality feature learning perspective and provides business value for consuming predictive analytics.