Developing a machine learning-based instrument for subjective well-being assessment on Weibo and its psychological significance: An evaluative and interpretive research.

Abstract

Demystifying machine learning (ML) approaches through the synergy of psychology and artificial intelligence can achieve a balance between predictive and explanatory power in model development while enhancing rigor in validation and reporting standards. Accordingly, this study aimed to bridge this research gap by developing a subjective well-being (SWB) prediction model on Weibo, serving as a psychological assessment instrument and explaining the model construction based on psychological knowledge. The model establishment involved the collection of SWB scores and posts from 1,427 valid Weibo users. Multiple machine learning algorithms were employed to train the model and fine-tune its parameters. The optimal model was selected by comparing its criterion validity and split-half reliability performance. Furthermore, SHAP values were calculated to rank the importance of features, which were then used for model interpretation. The criterion validity for the three dimensions of SWB ranged from 0.50 to 0.52 (P< 0.001), and the split-half reliability ranged from 0.94 to 0.96 (P< 0.001). The identified relevant features were related to four main aspects: cultural values, emotions, morality, and time and space. This study expands the application scope of SWB-related psychological theories from a data-driven perspective and provides a theoretical reference for further well-being prediction.