Testing the Effectiveness of AI Chatbots to Improve Public Knowledge and Attitudes Towards Depression

The Depression Literacy Scale is a 22-question survey that assesses a person's depression literacy. The questions are rated on a scale of "true", "false", or "I don't know". Each correct answer is worth one point, with higher scores indicating a higher level of depression literacy.

The Depression Literacy Questionnaire assesses mental health literacy specific to depression. It is a self-developed, 31-item questionnaire designed to assess participants' confidence in providing support to individuals experiencing depression. Each item is rated on a 5-point Likert scale, ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree"), with higher scores indicating greater depression literacy.

The Depression Stigma Scale is designed to measure stigma associated with depression. It has two subscales which measure two different types of stigma: personal and perceived. The Personal Stigma Subscale measures stigma in the respondents own attitudes towards depression by asking them to indicate how strongly they personally agree with nine statements about depression. The Perceived Stigma Subscale measures the respondent's perception about the attitudes of others towards depression by asking them to indicate what they think most other people believe about the same nine statements. Responses to each item are measured on a five-point scale (ranging from zero 'strongly disagree' to four 'strongly agree'). Higher scores indicate higher levels of depression stigma.

The Attribution Questionnaire (AQ) is a 9-item self-report assessment tool designed to measure public stigma towards people with mental illnesses. This version assesses emotional reaction and discriminatory responses based on answers to a hypothetical vignette about a man with depression named Xiao Li. Responses assessing stigma towards Xiao Li are in the form of 9 items rated on a Likert scale ranging from 1 (not at all) to 9 (very much).

The General Help-Seeking Questionnaire (GHSQ) in this study is an adapted 12-item version designed to fit Chinese cultural contexts. It assesses an individual's intentions to seek help for personal or emotional problems from both formal sources (e.g., mental health professionals, doctors) and informal sources (e.g., family, friends). Each item is rated on a 7-point Likert scale, ranging from 1 ("Extremely Unlikely") to 7 ("Extremely Likely"), with higher scores indicating a greater likelihood of seeking help.

The System Usability Scale (SUS) in this study is an adapted 9-item version designed to assess the usability of AI-based chatbots. It evaluates participants' perceptions of the ease of use, effectiveness, efficiency, and overall user experience of the chatbots. The scale uses a 5-point Likert scale, ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree"), with higher scores indicating better perceived usability. Participants will complete the adapted SUS separately for both the AI Depression Education Teacher and the AI Depression Patient Simulation ("Beibei"). The adapted SUS maintains the core usability assessment principles of the original scale while being tailored for AI-driven conversational agents.

The Confidence in Helping Others Scale is a self-developed, 19-item questionnaire designed to measure participants' confidence in providing support to individuals experiencing mental health issues. Each item is rated on a 5-point Likert scale, ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree"), with higher scores indicating greater confidence in recognizing depressive symptoms, offering emotional support, and encouraging help-seeking.

The Patient Health Questionnaire (PHQ-9) consists of 9 items designed to assess the severity of depressive symptoms over the past two weeks. Each item corresponds to one of the nine DSM-5 criteria for major depressive disorder and is rated on a 4-point Likert scale, ranging from 0 ("Not at all") to 3 ("Nearly every day"), with higher scores indicating greater symptom severity.

The Generalized Anxiety Disorder-7 (GAD-7) is a 7-item self-report questionnaire used to assess the severity of generalized anxiety symptoms over the past two weeks. Each item corresponds to common symptoms of generalized anxiety disorder (GAD) and is rated on a 4-point Likert scale, ranging from 0 ("Not at all") to 3 ("Nearly every day"), with higher scores indicating greater symptom severity.

The Basic Empathy Scale in Adults (BES-A) is a 20-item self-report questionnaire designed to assess an individual's capacity for empathy, including both cognitive empathy (understanding others' emotions) and affective empathy (sharing others' emotions). Each item is rated on a 5-point Likert scale, ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree"), with higher scores indicating greater empathy.

This questionnaire is self-conducted and assesses the frequency of various mental health-related behaviors over the past month. Participants rate each behavior based on how often they engaged in it, using a 5-point scale (0 = Never, 4 = More than 4 times per week). The results provide insight into individuals' proactive engagement in mental well-being practices.