EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Natural language processing of patient in-session speech to predict brief motivational interviewing alcohol intervention response: an exploratory study

Mahmoud Elsayed iD, Kyla L Belisario, Ashley Blakely, Sabrina K Syan iD, Emily Levitt, Molly Garber iD, Emily MacKillop, Iris Balodis, Lawrence H Sweet, James MacKillop iD

Alcohol and Alcoholism · 13.05.2026 · 61 (4)

DOI: 10.1093/alcalc/agag033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Alcohol and Alcoholism, online erschienen am 08.06.2026. Verfasst von Mahmoud Elsayed und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry and Behavioural Neurosciences, McMaster University, 1280 Main Street West, Hamilton, Ontario, L8S 4L8, Canada. Hauptthemen laut MEDLINE: Motivational Interviewing, Alcoholism, Natural Language Processing, Speech. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Peter Boris Chair in Addictions Research, Gary R. Sperduto Chair in Clinical Psychology, Canada Research Chair in Translational Addiction Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Motivational interviewing (MI) is a patient-centred, goal-oriented psychotherapy for alcohol use disorder (AUD) and numerous other conditions. While some language patterns have been linked to MI response, less is known about how broader linguistic features, sentiment, and engagement relate to post-intervention drinking. This study used natural language processing to examine these associations and clarify mechanisms through which MI for AUD exerts its effects.

Methods

Adults with AUD (N = 68) completed a single MI session with structured feedback and discussion of potential drinking changes. Speech transcripts were analysed for change-, emotion-, motivation-, substance-, and health-related words. Sentiment analysis assessed emotional polarity, and engagement was measured by total words spoken. Linear regression models tested associations between linguistic features and drinking outcomes, including drinks/week, percent heavy drinking days (%HDD), and percent drinking days (%DD).

Results

Participants showed significant reductions in drinks per week and %DD. Consistent with recent reviews of MI predictors, linguistic analyses found that greater use of change talk and health-related language was associated with more drinks per week at follow-up, whereas greater emotional talk and positive sentiment predicted fewer drinks per week. Health- and substance-related language predicted higher %HDD, while social motivation-related language predicted lower %DD. Term-frequency and multivariate analyses supported these patterns.

Conclusions

Via natural language processing of MI speech, linguistic features such as motivational content and sentiment were linked to drinking outcomes. Findings demonstrate the potential of this approach as a scalable, data-driven complement to traditional coding systems, with applications for real-time feedback, clinician training, and personalized interventions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Motivational InterviewingAlcoholismNatural Language ProcessingSpeechHumansMaleFemaleAdultMiddle AgedTreatment Outcome

Stichwörter der Autor:innen

alcohol use disorderlinguistic patternsmotivational interviewingnatural language processingsentiment analysistreatment outcomes

Autor:innen und Institutionen

  • Department of Psychiatry and Behavioural Neurosciences, McMaster University, 1280 Main Street West, Hamilton, Ontario, L8S 4L8, Canada.
  • Peter Boris Centre for Addictions Research, St. Joseph's Healthcare Hamilton, 100 West 5th Street, L9C 1G2, Hamilton, Canada.
  • Youth Wellness Centre, St. Joseph's Healthcare Hamilton, 38 James Street South, L8P 4W6, Hamilton, Canada.
  • Department of Psychology, University of Georgia, 125 Baldwin St, 30602, Athens, GA, United States.

ORCID-Profile: Mahmoud Elsayed, Sabrina K Syan, Molly Garber, James MacKillop

Förderung

  • Peter Boris Chair in Addictions Research
  • Gary R. Sperduto Chair in Clinical Psychology
  • Canada Research Chair in Translational Addiction Research
  • National Institute of Health

Zitieren

APA

Elsayed, M., Belisario, K. L., Blakely, A., Syan, S. K., Levitt, E., Garber, M., MacKillop, E., Balodis, I., Sweet, L. H., & MacKillop, J. (2026). Natural language processing of patient in-session speech to predict brief motivational interviewing alcohol intervention response: an exploratory study. Alcohol and Alcoholism, 61(4). https://doi.org/10.1093/alcalc/agag033

Vancouver

Elsayed M, Belisario KL, Blakely A, Syan SK, Levitt E, Garber M, et al. Natural language processing of patient in-session speech to predict brief motivational interviewing alcohol intervention response: an exploratory study. Alcohol and Alcoholism. 2026;61(4). doi:10.1093/alcalc/agag033

BibTeX
@article{Elsayed2026,
  author = {Elsayed, Mahmoud and Belisario, Kyla L and Blakely, Ashley and Syan, Sabrina K and Levitt, Emily and Garber, Molly and MacKillop, Emily and Balodis, Iris and Sweet, Lawrence H and MacKillop, James},
  title = {Natural language processing of patient in-session speech to predict brief motivational interviewing alcohol intervention response: an exploratory study},
  journal = {Alcohol and Alcoholism},
  year = {2026},
  volume = {61},
  number = {4},
  doi = {10.1093/alcalc/agag033}
}
Kostenlos starten →