Automatic Annotation of Dream Report’s Emotional Content with Large Language Models

In psychology and neuroscience, dreams are extensively studied both as a model to understand the neural bases of consciousness and for their relationship with psycho-physical well-being. The study of dream content typically relies on the analysis of verbal reports provided upon awakening. This task is classically performed through manual scoring provided by trained annotators, at a great time expense. While a consistent body of work suggests that natural language processing (NLP) tools can support the automatic analysis of dream reports, proposed methods lacked the ability to reason over a report’s full context and required extensive data pre-processing. Furthermore, in most cases, these methods were not validated against standard manual scoring approaches. In this work, we address these limitations by adopting large language models (LLMs) to study and replicate the manual annotation of dream reports, with a focus on reports’ emotions. Our results show that a text classification method based on BERT can achieve high performance, is resistant to biases, and shows promising results on data from a clinical population. Overall, results indicate that LLMs and NLP could find multiple successful applications in the analysis of large dream datasets and may favour reproducibility and comparability of results across research.