LLMs in qualitative psychology
Emerging applications of large language models in qualitative psychological research methodology as well as the critics.
Rathje, Steve et al. (2024)
GPT enables accurate, low-code multilingual detection of psychological constructs without task-specific training data.
The study tests GPT-3.5 Turbo, GPT-4, and GPT-4 Turbo on 47,925 manually annotated tweets and news headlines in 12 languages. Across sentiment, emotions, offensiveness, and moral foundations, GPT substantially outperformed English-language dictionary methods and approached or sometimes exceeded specialized fine-tuned models. Newer GPT versions improved performance, especially for lesser-spoken languages, while becoming less expensive. The findings suggest that prompt-based LLMs can make multilingual psychological text analysis more accessible for researchers without extensive coding skills or labeled training data.
Benchmarking GPT versions against manual labels, dictionary methods, and fine-tuned models across multilingual text datasets.
Basic familiarity with natural language processing, psychological text measures, and model evaluation.
One of the first uses of coding in psychology using LLMs
— ES