Natural language signatures of psilocybin microdosing
bioRxiv (Cold Spring Harbor Laboratory) February 22, 2022 Camila Sanz, Federico Cavanna, Stephanie Müller et al. 1 citation preprint
Low doses of psilocybin (microdoses) can be detected in natural speech. In a double-blind, placebo-controlled experiment, participants given 0.5 g of psilocybin mushrooms showed significant differences in verbosity and sentiment scores compared to placebo, though semantic variability did not differ. Machine learning classifiers using these speech metrics distinguished between the psilocybin and placebo conditions with high accuracy (AUC≈0.8). These findings suggest that unconstrained natural language may serve as a practical, low-cost tool for monitoring microdosing effects, addressing limitations of existing questionnaires designed for larger psychedelic doses.