Natural language signatures of psilocybin microdosing
Camila Sanz, Federico Cavanna, Stephanie Müller, Laura de la Fuente, Federico Zamberlán, Matías Palmucci, Lucie Janeckova, Martin Kuchař, Facundo Carrillo, Adolfo M. García, Carla Pallavicini, Enzo Tagliazucchi
bioRxiv (Cold Spring Harbor Laboratory) February 22, 2022 preprint DOI: 10.1101/2022.02.20.481177 via OpenAlex
Summary
AI-generated from the abstractLow 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.
Study at a glance
| Characteristics | Double-blind placebo-controlled experimental design |
|---|---|
| Intervention | Psilocybin mushrooms |
| Dose | 0.5 g of psilocybin mushrooms |
| Topics | Psilocybin |
| Keywords | Placebo Hallucinogen Psychology Microdose |
| Citations | 1 |
| Key finding | Natural language metrics—verbosity and sentiment scores—differed significantly between a 0.5 g psilocybin mushroom microdose and placebo, and machine learning classifiers distinguished the conditions with high accuracy (AUC≈0.8). |
Abstract
Abstract Serotonergic psychedelics are being studied as novel treatments for mental health disorders and as facilitators of improved well-being, mental function and creativity. Recent studies have found mixed results concerning the effects of low doses of psychedelics (“microdosing”) on these domains. However, microdosing is generally investigated using instruments designed to assess larger doses of psychedelics, which might lack sensitivity and specificity for this purpose. Following a double-blind and placebo-controlled experimental design, we explored natural language as a resource to identify speech produced under the acute effects of psilocybin microdoses, focusing on variables known to be affected by higher doses: verbosity, semantic variability and sentiment scores. Except for semantic variability, these metrics presented significant differences between a typical active microdose of 0.5 g of psilocybin mushrooms and an inactive placebo condition. Moreover, machine learning classifiers trained using these metrics were capable of distinguishing between conditions with high accuracy (AUC≈0.8). Our results constitute first proof that low doses of serotonergic psychedelics can be identified from unconstrained natural speech, with potential for widely applicable, affordable, and ecologically valid monitoring of microdosing schedules.