Unsupervised Extractive Summarization of Psychedelic User Experience Reports
medRxiv August 27, 2025 Md. Shahidul Islam, Md Sakib Ibne Salam, Md Nahid Hasan 1 citation preprint
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.