Matthew Russell Bennion 1 , Gillian E Hardy 1 , Roger K Moore 2 , Stephen Kellett 1 , Abigail Millings 1 Show Affiliations »
Abstract
Show RCT »
Hide RCT «
BACKGROUND: The usability and effectiveness of conversational agents (chatbots ) that deliver psychological therapies is under-researched. OBJECTIVE: This study aimed to compare the system usability, acceptability, and effectiveness in older adults of 2 Web-based conversational agents that differ in theoretical orientation and approach. METHODS: In a randomized study, 112 older adults were allocated to 1 of the following 2 fully automated interventions: Manage Your Life Online (MYLO; ie, a chatbot that mimics a therapist using a method of levels approach) and ELIZA (a chatbot that mimics a therapist using a humanistic counseling approach ). The primary outcome was problem distress and resolution, with secondary outcome measures of system usability and clinical outcome . RESULTS: MYLO participants spent significantly longer interacting with the conversational agent. Posthoc tests indicated that MYLO participants had significantly lower problem distress at follow-up. There were no differences between MYLO and ELIZA in terms of problem resolution. MYLO was rated as significantly more helpful and likely to be used again. System usability of both the conversational agents was associated with helpfulness of the agents and the willingness of the participants to reuse. Adherence was high. A total of 12% (7/59) of the MYLO group did not carry out their conversation with the chatbot. CONCLUSIONS: Controlled studies of chatbots need to be conducted in clinical populations across different age groups. The potential integration of chatbots into psychological care in routine services is discussed. ©Matthew Russell Bennion, Gillian E Hardy, Roger K Moore, Stephen Kellett, Abigail Millings. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 27.05.2020.
RCT Entities: Population
Interventions
Outcomes
BACKGROUND: The usability and effectiveness of conversational agents (chatbots) that deliver psychological therapies is under-researched. OBJECTIVE: This study aimed to compare the system usability, acceptability, and effectiveness in older adults of 2 Web-based conversational agents that differ in theoretical orientation and approach. METHODS: In a randomized study, 112 older adults were allocated to 1 of the following 2 fully automated interventions: Manage Your Life Online (MYLO; ie, a chatbot that mimics a therapist using a method of levels approach) and ELIZA (a chatbot that mimics a therapist using a humanistic counseling approach). The primary outcome was problem distress and resolution, with secondary outcome measures of system usability and clinical outcome. RESULTS: MYLO participants spent significantly longer interacting with the conversational agent. Posthoc tests indicated that MYLO participants had significantly lower problem distress at follow-up. There were no differences between MYLO and ELIZA in terms of problem resolution. MYLO was rated as significantly more helpful and likely to be used again. System usability of both the conversational agents was associated with helpfulness of the agents and the willingness of the participants to reuse. Adherence was high. A total of 12% (7/59) of the MYLO group did not carry out their conversation with the chatbot. CONCLUSIONS: Controlled studies of chatbots need to be conducted in clinical populations across different age groups. The potential integration of chatbots into psychological care in routine services is discussed. ©Matthew Russell Bennion, Gillian E Hardy, Roger K Moore, Stephen Kellett, Abigail Millings. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 27.05.2020.
Entities: Chemical
Disease
Gene
Species
Keywords:
acceptability; chatbots; conversational agents; effectiveness; mental health; method of levels; older adults; system usability; transdiagnostic; web-based
Year: 2020
PMID： 32384055 DOI： 10.2196/16794
Source DB: PubMed Journal: J Med Internet Res ISSN： 1438-8871 Impact factor: 5.428