Artificial Intelligence Chatbot for Depression: Descriptive Study of Usage
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it