Robert E. Kraut

Online mental health support communities have grown in recent years for providing accessible mental and emotional health support through volunteer counselors. Despite millions of people participating in chat support on these platforms, the clinical effectiveness of these communities on mental health symptoms remains unknown. Furthermore, although volunteers receive some training based on established therapeutic skills studied in face-to-face environments such as active listening and motivational interviewing, it remains understudied how the usage of these skills in this online context affects people's mental health status. In our work, we collaborate with one of the largest online peer support platforms and use both natural language processing and machine learning techniques to measure how one-on-one support chats affect depression and anxiety symptoms. We measure how the techniques and characteristics of support providers, such as using affirmation, empathy, and past experience on the platform, affect support-seekers' mental health changes. We find that online peer support chats improve both depression and anxiety symptoms with a statistically significant but relatively small effect size. Additionally, support providers' techniques such as emphasizing the autonomy of the client lead to better mental health outcomes. However, we also found that some behaviors (e.g. persuading) are actually harmful to depression and anxiety outcomes. Our work provides key understanding for mental health care in the online setting and designing training systems for online support providers.

Realistic practice and tailored feedback are key processes for training peer counselors with clinical skills. However, existing mechanisms of providing feedback largely rely on human supervision. Peer counselors often lack mechanisms to receive detailed feedback from experienced mentors, making it difficult for them to support the large number of people with mental health issues who use peer counseling. Our work aims to leverage large language models to provide contextualized and multi-level feedback to empower peer counselors, especially novices, at scale. To achieve this, we co-design with a group of senior psychotherapy supervisors to develop a multi-level feedback taxonomy, and then construct a publicly available dataset with comprehensive feedback annotations of 400 emotional support conversations. We further design a self-improvement method on top of large language models to enhance the automatic generation of feedback. Via qualitative and quantitative evaluation with domain experts, we demonstrate that our method minimizes the risk of potentially harmful and low-quality feedback generation which is desirable in such high-stakes scenarios.

Online mental health communities (OMHCs) are an effective and accessible channel to give and receive social support for individuals with mental and emotional issues. However, a key challenge on these platforms is finding suitable partners to interact with given that mechanisms to match users are currently underdeveloped. In this paper, we collaborate with one of the world's largest OMHC to develop an agent-based simulation framework and explore the trade-offs in different matching algorithms. The simulation framework allows us to compare current mechanisms and new algorithmic matching policies on the platform, and observe their differing effects on a variety of outcome metrics. Our findings include that usage of the deferred-acceptance algorithm can significantly better the experiences of support-seekers in one-on-one chats while maintaining low waiting time. We note key design considerations that agent-based modeling reveals in the OMHC context, including the potential benefits of algorithmic matching on marginalized communities.

Wikipedia has been the poster child for large-scale online open collaboration while few other online open collaboration initiatives have achieved similar success. How did Wikipedians do it? Besides the technical infrastructure, what social dynamics and processes are critical to its success? This essay reviews 217 articles that examined aspects of the behaviors of Wikipedia editors and the processes through which they coordinate and collaborate. Using the Input-Mediator-Output-Input model (IMOI) as the organizing framework, we summarized the key insights in an integrative review. The input factors include editors, their motivations, and the tools they use to support their work. The mediating factors include coordination, governance, leadership, conflict, newcomer socialization, and roles. The outcome focuses on measuring and predicting contribution quantity and quality. We hope our work serves as a road map for …

What people see on social media influences their affective state. Predictions of the affective reaction of an audience to a post could help posters creating content and viewers searching for it. This paper examines the value of both real comments and artificially generated ones in predicting the affective responses of an audience. We built an affect prediction model based on Facebook anonymized public posts to predict affective responses (anger, amusement, and sadness affect) as indicated by three Facebook reaction clicks (Angry, Haha, and Sad). Using the content of the original post can predict reactions well (.71 to.87 F1-scores). Adding the text of real post comments improves F1-score by up to 11%. Surprisingly, generated comments improve predictions as much as real comments. These artificial comments were produced using a pre-trained sequence-to-sequence, BART natural language generation model …

Main effect models contend that perceived social support benefits mental health in the presence and the absence of stressful events, whereas stress-buffering models contend that perceived social support benefits mental health especially when individuals are facing stressful events. We tested these models of how perceived social support impacts mental health during the COVID-19 pandemic and evaluated whether characteristics of everyday social interactions statistically mediated this association – namely, (a) received support, the visible and deliberate assistance provided by others, and (b) pleasantness, the extent to which an interaction is positive, flows easily, and leads individuals to feel understood and validated. 591 United States adults completed a 3-week ecological momentary assessment protocol sampling characteristics of their everyday social interactions that was used to evaluate between-person …

Experiential training, where mental health professionals practice their learned skills, remains the most costly component of therapeutic training. We introduce Pin-MI, a video-call-based tool that supports experiential learning of counseling skills used in motivational interviewing (MI)through interactive role-play as client and counselor. In Pin-MI, counselors annotate, or “pin” the important moments in their role-play sessions in real-time. The pins are then used post-session to facilitate a reflective learning process, in which both client and counselor can provide feedback about what went well or poorly during each pinned moment. We discuss the design of Pin-MI and a qualitative evaluation with a set of healthcare professionals learning MI. Our evaluation suggests that Pin-MI helped users develop empathy, be more aware of their skill usage, guaranteed immediate and targeted feedback, and helped users correct …

Conversational artificial intelligence (AI), particularly AI-based conversational agents (CAs), is gaining traction in mental health care. Despite their growing usage, there is a scarcity of comprehensive evaluations of their impact on mental health and well-being. This systematic review and meta-analysis aims to fill this gap by synthesizing evidence on the effectiveness of AI-based CAs in improving mental health and factors influencing their effectiveness and user experience. Twelve databases were searched for experimental studies of AI-based CAs’ effects on mental illnesses and psychological well-being published before May 26, 2023. Out of 7834 records, 35 eligible studies were identified for systematic review, out of which 15 randomized controlled trials were included for meta-analysis. The meta-analysis revealed that AI-based CAs significantly reduce symptoms of depression (Hedge’s g 0.64 [95% CI 0.17–1.12 …