Chatbot for Online Support Groups to Treat Tobacco Addiction

NCT06952725 | Not Yet Recruiting

• 1 other identifier: 919
• Study Type: interventional
• Target: 120
• Locations: 0 countries
• Sites: N/A

Brief Summary

Investigators will conduct a pilot RCT to test the efficacy of an intelligent chatbot to aid small, private, quit-smoking peer support groups. Participants will be randomized to an intervention arm (chatbot-enhanced support group), or a control arm (support group only). In the intervention arm (N=60), each support group will be connected to an intelligent chatbot running on a secure local server as a trained LLM (large language model). The intelligent chatbot will function as an additional member of the GroupMe support group, but a member that only responds if no human does so. In the control arm (N=60), the support groups will be connected to an automated message-posting bot running on a secure local server. This automated message-posting bot will lack the response capabilities of the intelligent chatbot. But both the intelligent chatbot and the automated message-posting bot will post a pre-written daily discussion topic to encourage participants to discuss issues known to facilitate tobacco cessation or group bonding.

Conditions

Tobacco Dependence; Tobacco Use Disorder

Keywords

tobacco use addiction; online support group; chatbot

Outcome Measures

Primary Outcomes (1)

• Overall posts per participant

  Each night, our study website will download each group's past 24-hour posts in both the test and control conditions labeled by date and poster.

  End of 90-day intervention

Secondary Outcomes (3)

• Bio-confirmed smoking abstinence

  End of 90-day intervention

• NRT use at 1-month

  30 days after intervention start

• nrt use at intervention end

  End of 90-day intervention

Study Arms (2)

test: support group with intelligent chatbot

EXPERIMENTAL

When participants post to their support groups, the intelligent chatbot will detect relevant post types and generate responses which will be posted back to them and their group, if no human responds to the post within about 10 seconds. The intelligent chatbot will also post a daily discussion topic.

Behavioral: online quit-smoking support group with intelligent chatbot

control: support group with unintelligent bot

ACTIVE COMPARATOR

The unintelligent chatbot will not respond to participants' posts; it will merely post a daily discussion topic.

Behavioral: online quit-smoking support group with unintelligent bot

Interventions

online quit-smoking support group with intelligent chatbot BEHAVIORAL

In the intervention arm (N=60), each quit-smoking peer support group will be connected to an intelligent chatbot running on a secure local server as a trained LLM (large language model). This chatbot will monitor all posts in the group and seek to comprehend these posts using the training it has been provided. If a group member makes a post and no one responds with about 10 seconds, the chatbot will respond using one of its 25 response libraries created from knowledge bases, which contain over 1k responses in total. In effect, the intelligent chatbot will function as an additional member of the GroupMe support group, but a member that only responds if no human does so.

test: support group with intelligent chatbot

online quit-smoking support group with unintelligent bot BEHAVIORAL

In the control arm (N=60), the support groups will be connected to our original automated message-posting bot running on our secure local server. This automated message-posting bot will lack the response capabilities of the intelligent chatbot; it will not respond to posts if no human group member does but, instead, remain silent. However, it will post the same daily discussion topic, and at the same time of day, as the intelligent chatbot.

control: support group with unintelligent bot

Eligibility Criteria

• Age: 18 Years - 75 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Cigarette smokers (can also use e-cigarettes)
• Ages 18-75 years
• English speaking
• Smart phone with unlimited data
• cigarettes lifetime
• Prepared to quit smoking within 10 days of study start
• Active text and email
• Use of social media or group messaging
• Home address provided
• Contact information for a collateral provided
• Setup of a GroupMe account for study

You may not qualify if:

• No NRT health contraindications
• + cigarettes per day
• Not an illicit drug user
• Not a daily marijuana/cannabis user

Sponsors & Collaborators

• University of California, Irvine: lead

Related Publications (8)

• Giyahchi T, Singh S, Harris I, Pechmann C. Customized training of pretrained language models to detect post intents in online health support groups. In: Shaban-Nejad A, Michalowski M, Bianco S, eds. Multimodal AI in Healthcare Studies in Computational Intelligence. Springer Nature; 2023:59-76:chap 14.

  BACKGROUND

• Prochaska JJ, Vogel EA, Chieng A, Kendra M, Baiocchi M, Pajarito S, Robinson A. A Therapeutic Relational Agent for Reducing Problematic Substance Use (Woebot): Development and Usability Study. J Med Internet Res. 2021 Mar 23;23(3):e24850. doi: 10.2196/24850.

  PMID: 33755028 BACKGROUND

• Phillips C, Pechmann C, Calder D, Prochaska JJ. Understanding Hesitation to Use Nicotine Replacement Therapy: A Content Analysis of Posts in Online Tobacco-Cessation Support Groups. Am J Health Promot. 2023 Jan;37(1):30-38. doi: 10.1177/08901171221113835. Epub 2022 Jul 11.

  PMID: 35817548 BACKGROUND

• Pechmann CC, Yoon KE, Trapido D, Prochaska JJ. Perceived Costs versus Actual Benefits of Demographic Self-Disclosure in Online Support Groups. J Consum Psychol. 2021 Jul;31(3):450-477. doi: 10.1002/jcpy.1200. Epub 2020 Oct 19.

  PMID: 36276230 BACKGROUND

• Pechmann C, Pan L, Delucchi K, Lakon CM, Prochaska JJ. Development of a Twitter-based intervention for smoking cessation that encourages high-quality social media interactions via automessages. J Med Internet Res. 2015 Feb 23;17(2):e50. doi: 10.2196/jmir.3772.

  PMID: 25707037 BACKGROUND

• Pechmann C, Delucchi K, Lakon CM, Prochaska JJ. Randomised controlled trial evaluation of Tweet2Quit: a social network quit-smoking intervention. Tob Control. 2017 Mar;26(2):188-194. doi: 10.1136/tobaccocontrol-2015-052768. Epub 2016 Feb 29.

  PMID: 26928205 BACKGROUND

• Lakon CM, Pechmann C, Wang C, Pan L, Delucchi K, Prochaska JJ. Mapping Engagement in Twitter-Based Support Networks for Adult Smoking Cessation. Am J Public Health. 2016 Aug;106(8):1374-80. doi: 10.2105/AJPH.2016.303256. Epub 2016 Jun 16.

  PMID: 27310342 BACKGROUND

• Esmaeeli A, Pechmann CC, Prochaska JJ. Buddies as In-Group Influencers in Online Support Groups: A Social Network Analysis of Processes and Outcomes. J Interact Market. 2022 May;57(2):198-211. doi: 10.1177/10949968221076144. Epub 2022 Apr 26.

  PMID: 35656556 BACKGROUND

MeSH Terms

Conditions

Tobacco Use Disorder

Condition Hierarchy (Ancestors)

Substance-Related Disorders; Chemically-Induced Disorders; Mental Disorders

Study Officials

• Cornelia A. Pechmann, PhD

  University of California, Irvine

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Cornelia A Pechmann, PhD

CONTACT

3108920619; cpechman@uci.edu

Ian G. Harris, PhD

CONTACT

9498248842; harris@ics.uci.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: April 23, 2025
• First Posted: May 1, 2025
• Study Start (Estimated): December 1, 2026
• Primary Completion (Estimated): June 1, 2028
• Study Completion (Estimated): June 1, 2028
• Last Updated: May 11, 2025

Record last verified: 2025-05

Data Sharing

• IPD Sharing: Will not share