Artificial Intelligence Chatbot for Depression: Descriptive Study of Usage

Abstract

Background: Chatbots could be a scalable solution that provides an interactive means of engaging users in behavioral health interventions driven by artificial intelligence. Although some chatbots have shown promising early efficacy results, there is limited information about how people use these chatbots. Understanding the usage patterns of chatbots for depression represents a crucial step toward improving chatbot design and providing information about the strengths and limitations of the chatbots.

Objective: This study aims to understand how users engage and are redirected through a chatbot for depression (Tess) to provide design recommendations.

Methods: Interactions of 354 users with the Tess depression modules were analyzed to understand chatbot usage across and within modules. Descriptive statistics were used to analyze participant flow through each depression module, including characters per message, completion rate, and time spent per module. Slide plots were also used to analyze the flow across and within modules.

Results: Users sent a total of 6220 messages, with a total of 86,298 characters, and, on average, they engaged with Tess depression modules for 46 days. There was large heterogeneity in user engagement across different modules, which appeared to be affected by the length, complexity, content, and style of questions within the modules and the routing between modules.

Conclusions: Overall, participants engaged with Tess; however, there was a heterogeneous usage pattern because of varying module designs. Major implications for future chatbot design and evaluation are discussed in the paper.

Keywords: artificial intelligence; chatbot; depression; mobile health; telehealth.

Figure 1

A sample transcript of a participant interacting with Tess.

Figure 2

Modules initiated by Tess. The figure presents the first 5 module steps that participants interacted with that were initiated by Tess. The timeline reflects the module number to which the participant was exposed (ie, timeline 1 is the module that people started with, and timeline 2 is the second module that participants began). The line thickness describes the transitions from one module to the next and not the number of users in a given module. Body-scan: body scan; Cog-dis: cognitive distortion; Compassion: self-compassion; Cope-state: coping statements; Dep-diet: depression diet; Rad-accept: radical acceptance; Self-soothe: self-soothing; Sol-foc: solution focus; Tht-jrnl: thought journaling; Trans-T: transtheoretical.

Figure 3

Modules initiated by user. The figure presents the first 5 module steps that participants interacted with that were initiated by the participant. The timeline reflects the module number to which the participant was exposed (ie, timeline 1 is the module that people started with, and timeline 2 is the second module that participants began). The line thickness describes the transitions from one module to the next and not the number of users in a given module. Body-scan: body scan; Cog-dis: cognitive distortion; Compassion: self-compassion; Cope-state: coping statements; Dep-diet: depression diet; Rad-accept: radical acceptance; Self-soothe: self-soothing; Sol-foc: solution focus; Tht-jrnl: thought journaling; Trans-T: transtheoretical.

Figure 4

User flow through the body scan module. The timeline reflects the module number to which the participant was exposed. Frequencies are based on messages sent by the participant in association with each module question sent by Tess. The line thickness describes the transitions from one module to the next and not the number of users in a given module.

Figure 5

User flow through the cognitive distortion module. The timeline reflects the module number to which the participant was exposed. Frequencies are based on messages sent by the participant in association with each module question sent by Tess. The line thickness describes the transitions from one module to the next and not the number of users in a given module.