Dreams Are More "Predictable'' Than You Think
This addresses a potential issue for NLP tools in dream research by showing dream reports are not as unique as believed, which is incremental for improving automated analysis methods.
The study investigated whether dream reports are more predictable than other human-generated text like Wikipedia using large language models, finding that single dream reports are significantly more predictable on average, with factors like word count, gender, and visual impairment influencing predictability.
A consistent body of evidence suggests that dream reports significantly vary from other types of textual transcripts with respect to semantic content. Furthermore, it appears to be a widespread belief in the dream/sleep research community that dream reports constitute rather ``unique'' strings of text. This might be a notable issue for the growing amount of approaches using natural language processing (NLP) tools to automatically analyse dream reports, as they largely rely on neural models trained on non-dream corpora scraped from the web. In this work, I will adopt state-of-the-art (SotA) large language models (LLMs), to study if and how dream reports deviate from other human-generated text strings, such as Wikipedia. Results show that, taken as a whole, DreamBank does not deviate from Wikipedia. Moreover, on average, single dream reports are significantly more predictable than Wikipedia articles. Preliminary evidence suggests that word count, gender, and visual impairment can significantly shape how predictable a dream report can appear to the model.