- 156 views
- 141 downloads
The Development and Evaluation of a Frequently-Asked Question (FAQ) Answering Chatbot for an Online Mental Wellness Program for People with Chronic Disease
-
- Author / Creator
- Sadasivan, Chikku
-
Introduction: Chatbots are computer programs that interact with humans through natural language conversations. Chatbots are on the rise due to numerous benefits like convenience, 24/7, personalized support, and they show promise in healthcare to support people living with chronic diseases. While chatbots, like other digital health interventions, are promising tools for chronic disease management, they also face challenges such as limited user adoption and low engagement. One way to address these challenges is to involve patients in development.
Objectives: The purpose of these studies was to report the non-technical (e.g. non-software development related) approaches for chatbot creation while examining patient engagement in these approaches and to develop the FAQ chatbot and evaluate its acceptability, usability, and user engagement through a multi-method approach.
Methods: In Chapter 3, our team conducted a scoping review following the framework proposed by Arksey and O’Malley. Nine electronic databases were searched in July 2022. Studies were selected based on our inclusion/exclusion criteria. Data were then extracted, and patient involvement was assessed. In Chapter 4, a FAQ-answering chatbot (“Liv”) was developed from May 2022 to February 2023 and evaluated through a multi-phased, multi-method design. Liv was then deployed on an online mental wellness program and evaluated for acceptability, usability, and user engagement.
Results: In Chapter 3, 16 studies were included in the review. We report several approaches to chatbot development, assess patient involvement where possible, and reveal the limited detail available on reporting patient involvement in the chatbot implementation process. In Chapter 4, Liv was deployed for 120 days, and there were 259 conversations with Liv, with 175 instances of active engagement (back-and-forth user-chatbot interaction). Engagement was highest during the first 30 days of deployment. The chatbot had a resolution rate of 33%. Liv’s usability was evaluated with an overall score of 50.8 (below average), with successes in specific areas, including its navigation and ease of use. Findings from qualitative interviews included comments on Liv’s personality, the convenience of knowing the chatbot would escalate, and experiences with Liv and her improvement over time.
Conclusion: FAQ chatbots may be an engaging way to provide patient support in online mental wellness programming. Including patients in development may improve chatbot acceptability, usability, and user engagement. Future work that prioritizes patient engagement in the development and builds upon conversation log data to create a more advanced bot is warranted.
-
- Subjects / Keywords
-
- Graduation date
- Fall 2023
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.