Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Formative Research

Date Submitted: Jul 7, 2020
Open Peer Review Period: May 25, 2020 - Jul 20, 2020
Date Accepted: May 29, 2021
Date Submitted to PubMed: Aug 13, 2021
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

Artificial Intelligence–Based Chatbot for Anxiety and Depression in University Students: Pilot Randomized Controlled Trial

Klos MC, Escoredo M, Joerin A, Lemos VN, Rauws M, Bunge EL

Artificial Intelligence–Based Chatbot for Anxiety and Depression in University Students: Pilot Randomized Controlled Trial

JMIR Form Res 2021;5(8):e20678

DOI: 10.2196/20678

PMID: 34092548

PMCID: 8391753

Artificial Intelligence Chatbot for Anxiety and Depression in University Students: a Pilot Randomized Controlled Trial

  • Maria Carolina Klos; 
  • Milagros Escoredo; 
  • Angie Joerin; 
  • Viviana Noemí Lemos; 
  • Michiel Rauws; 
  • Eduardo L. Bunge

ABSTRACT

Background:

The use of artificial intelligence based chatbots as an instrument of psychological intervention is emerging, however no studies have been reported in Latin America.

Objective:

This study aims to evaluate usage patterns and whether the use of a chatbot is effective for relieving depression and anxiety symptoms compared to a control group utilizing a psychoeducation book in Argentina.

Methods:

This was a randomized controlled trial study utilizing the chabot Tess throughout eight weeks. The initial sample consisted of 181 Argentinian college students ages 18 to 33, 87.2% female. Of those, 33 participants in the experimental condition and 30 in the control condition provided data on depressive symptoms at week eight, and 27 participants in the experimental condition and 23 in the control condition provided data on anxiety symptoms at week eight. Between and within group comparisons were analysed using Mann-Whitney U and Wilcoxon tests for depression symptoms, and Independent and Paired Samples t Tests to analyze anxiety symptoms.

Results:

There was no significant intergroup differences between the experimental group and the control group for depression and anxiety symptoms from baseline to week eight (P>.05). However, there were significant intragroup differences, where the experimental group showed a significant decrease in anxiety symptoms (P=.04) and no differences were observed for the control group (P=.33). No significant differences were found for depressive symptoms within the groups (P>.05). The effect size of the intervention was moderate for anxiety (d=.50) and small for depression (r=.09). In regards to participants engagement after eight weeks, there was an average of 472 exchanged messages (M=472.15; SD=249.52) and a higher number of messages exchanged with Tess was associated with positive feedback (F2,36=4.37; P=.02).

Conclusions:

Students engaged a considerable amount of time exchanging messages with Tess and positive feedback was associated with higher numbers of messages exchanged. The initial results show promising evidence for the use of Tess for anxiety symptoms and a lower effect on depressive symptoms in Argentinian college students. Research on chatbots is still in its initial stages and further research is needed.


 Citation

Please cite as:

Klos MC, Escoredo M, Joerin A, Lemos VN, Rauws M, Bunge EL

Artificial Intelligence–Based Chatbot for Anxiety and Depression in University Students: Pilot Randomized Controlled Trial

JMIR Form Res 2021;5(8):e20678

DOI: 10.2196/20678

PMID: 34092548

PMCID: 8391753

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.