Predicting changes in substance use following psychedelic experiences: natural language processing of psychedelic session narratives
The American Journal of Drug and Alcohol Abuse June 5, 2021 David J. Cox, Albert Garcia-Romeu, Matthew W. Johnson 29 citations
People who quit or reduced using alcohol, cannabis, opioids, or stimulants after a psychedelic experience provided written narratives of that experience. Natural language processing extracted topic models from the narratives, and three machine learning algorithms predicted long-term drug reduction outcomes with about 65% accuracy. The quantitative descriptions of the experiences differed depending on which drug class was quit and whether the reduction was sustained. The findings suggest that analyzing written reports of psychedelic experiences with machine learning could help predict who will benefit from psychedelic therapy for substance use.