Development and Evaluation of HopeBot: an LLM-based chatbot for structured and interactive PHQ-9 depression screening

TL;DR

HopeBot is an LLM-powered chatbot that administers the PHQ-9 depression screening tool interactively, showing high agreement with traditional methods and high user trust, suggesting its potential as a scalable mental health screening adjunct.

Contribution

This paper introduces HopeBot, a novel LLM-based chatbot that enhances depression screening with interactivity, real-time clarification, and retrieval-augmented generation, improving user trust and engagement.

Findings

Strong agreement with self-administered PHQ-9 scores (ICC=0.91)

Majority of users trusted and preferred the chatbot approach

High willingness to reuse or recommend HopeBot (87.1%)

Abstract

Static tools like the Patient Health Questionnaire-9 (PHQ-9) effectively screen depression but lack interactivity and adaptability. We developed HopeBot, a chatbot powered by a large language model (LLM) that administers the PHQ-9 using retrieval-augmented generation and real-time clarification. In a within-subject study, 132 adults in the United Kingdom and China completed both self-administered and chatbot versions. Scores demonstrated strong agreement (ICC = 0.91; 45% identical). Among 75 participants providing comparative feedback, 71% reported greater trust in the chatbot, highlighting clearer structure, interpretive guidance, and a supportive tone. Mean ratings (0-10) were 8.4 for comfort, 7.7 for voice clarity, 7.6 for handling sensitive topics, and 7.4 for recommendation helpfulness; the latter varied significantly by employment status and prior mental-health service use (p < 0.05). Overall, 87.1% expressed willingness to reuse or recommend HopeBot. These findings demonstrate voice-based LLM chatbots can feasibly serve as scalable, low-burden adjuncts for routine depression screening.