Unsupervised Extractive Summarization of Psychedelic User Experience Reports

Unsupervised automatic text summarization was applied to 1,200 user experience reports of LSD, psilocybin, and DMT. Three extractive methods—LexRank, LSA with HDBSCAN clustering, and SBERT with Maximal Marginal Relevance—were compared using a custom scoring function that measures semantic coverage, narrative coherence, and experiential preservation. LexRank achieved the best overall balance, while SBERT excelled in content coverage and experiential depth but lacked coherence. Trade-offs between content richness and narrative fluency varied across substances due to differences in narrative structure. The study suggests that extractive summarization can help make subjective psychedelic reports more clinically useful, though future work should explore abstractive methods and expert adjudication.

Study at a glance

Abstract

A bstract Contemporary psychedelic research highlights the value of user experience reports, yet their verbose, subjective nature poses challenges for clinical utility. This is the first study to pioneer unsupervised automatic text summarization of psychedelic user experience reports, a domain where no human-annotated reference summaries exist. To address this gap, we developed a custom scoring function that integrates semantic coverage, narrative coherence, and a novel experiential preservation metric, enabling effective model training and hyperparameter tuning. We utilized three established extractive methods: LexRank, LSA with HDBSCAN clustering, and SBERT with Maximal Marginal Relevance, on 1,200 reports involving LSD, psilocybin, and DMT. Using GPT-4 as a calibrated rater under a structured rubric, supplemented by TOPSIS aggregation, results showed LexRank achieving the highest overall balance with SBERT excelling in content coverage and experiential depth but lagging in coherence. Our findings revealed trade-offs between content richness and narrative fluency, with performance varying across substance types due to differences in narrative structure and phenomenology. Limitations included reliance on extractive methods, lack of reference data, and sensitivity to scoring design. Future work should extend to abstractive methods, alternative weighting schemes, and expert adjudication to develop clinically usable summarization systems for psychedelic science.