# Automatic Scoring of Dream Reports' Emotional Content with Large Language Models

## TL;DR

This paper explores the use of large language models to automatically analyze and score the emotional content of dream reports, aiming to improve efficiency and consistency over manual methods.

## Contribution

It introduces a novel bespoke LLM-based approach for emotion classification in dream reports, outperforming off-the-shelf models and addressing previous limitations.

## Key findings

- Bespoke method achieves high, robust performance.
- Off-the-shelf models perform poorly due to linguistic differences.
- Approach facilitates large-scale dream data analysis and reproducibility.

## Abstract

In the field of dream research, the study of dream content typically relies on the analysis of verbal reports provided by dreamers upon awakening from their sleep. 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, using a mixture of off-the-shelf and bespoke approaches, with a focus on references to reports' emotions. Our results show that the off-the-shelf method achieves a low performance probably in light of inherent linguistic differences between reports collected in different (groups of) individuals. On the other hand, the proposed bespoke text classification method achieves a high performance, which is robust against potential biases. Overall, these observations indicate that our approach could find application in the analysis of large dream datasets and may favour reproducibility and comparability of results across studies.