From Pre-trained Models to Large Language Models: A Comprehensive Survey of AI-Driven Psychological Computing
It addresses the problem of isolated development in computational psychology for researchers, enabling systematic knowledge transfer and accelerated progress.
This survey tackles the methodological fragmentation in AI-driven psychology by introducing a systematic taxonomy that organizes tasks by computational patterns rather than domains, analyzing over 300 works to show the evolution from feature engineering to few-shot adaptation.
The intersection of artificial intelligence and psychological science has experienced remarkable growth, with annual publications expanding from 859 papers in 2000 to 29,979 by 2025. However, this rapid evolution has created methodological fragmentation where similar computational techniques are independently developed across isolated psychological domains. This survey introduces the first systematic taxonomy that organizes AI-driven psychology tasks by computational processing patterns rather than application domains, categorizing them into four fundamental types: classification, regression, structured relational, and generative interactive tasks. Through analysis of over 300 representative works spanning the pre-trained model era and large language model era, we examine how computational approaches evolved from task-specific feature engineering to transfer learning and few-shot adaptation. We provide systematic coverage of datasets, evaluation metrics, and benchmarks while addressing fundamental challenges including interpretability, label uncertainty, privacy constraints, and cross-cultural validity. This computational perspective reveals transferable methodological patterns previously obscured by domain-centric organization, enabling systematic knowledge transfer and accelerated progress in computational psychology.