Psychotherapy delivery relies on a negotiation between patient self-reports and clinical intuition. Growing evidence for technological support of psychotherapy suggests opportunities to aid the mediation of this tension. To explore this prospect, we designed a prototype of a clinical decision support system (CDSS) for treating veterans with post-traumatic stress disorder in a Prolonged Exposure (PE) therapy intensive outpatient program. We conducted a two-phase interview study to collect perspectives from practicing PE clinicians and former PE patients who are United States veterans. Our analysis distills opportunities for a CDSS (e.g., offering homework review at a glance, aiding patient conceptualization) and larger challenges related to context and deployment (e.g., navigating Veterans Affairs). By reframing our findings through three human-centered perspectives (distributed cognition, situated learning, infrastructural inversion), we highlight the complexities of designing a CDSS for psychotherapists in this context and offer theory-aligned design considerations.

Role-play exercises are widely utilized for training across a variety of domains; however, they have many shortcomings, including low availability, resource intensity, and lack of diversity. Large language model-driven virtual agents offer a potential avenue to mitigate these limitations and offer lower-risk role-play. The implications, however, of shifting this human-human collaboration to human-agent collaboration are still largely unexplored. In this work we focus on the context of psychotherapy, as psychotherapists-in-training extensively engage in role-play exercises with peers and/or supervisors to practice the interpersonal and therapeutic skills required for effective treatment. We provide a case study of a realistic ''virtual patient'' system for mental health training, evaluated by trained psychotherapists in comparison to their previous experiences with both real role-play partners and real patients. Our qualitative, reflexive analysis generated three themes and thirteen subthemes regarding key interpersonal skills of psychotherapy, the utility of the system compared to traditional role-play techniques, and factors which impacted psychotherapist-perceived ''humanness'' of the virtual patient. Although psychotherapists were optimistic about the system's potential to bolster therapeutic skills, this utility was impacted by the extent to which the virtual patient was perceived as human-like. We leverage the Computers Are Social Actors framework to discuss human-virtual-patient collaboration for practicing rapport, and discuss challenges of prototyping novel human-AI systems for clinical contexts which require a high degree of unpredictability. We pull from the ''SEEK'' three-factor theory of anthropomorphism to stress the importance of adequately representing a variety of cultural communities within mental health AI systems, in alignment with decolonial computing.

The mental health crisis in the United States spotlights the need for more scalable training for mental health workers. While present-day AI systems have sparked hope for addressing this problem, we must not be too quick to incorporate or solely focus on technological advancements. We must ask empirical questions about how to ethically collaborate with and integrate autonomous AI into the clinical workplace. For these Human-Autonomy Teams (HATs), poised to make the leap into the mental health domain, special consideration around the construct of trust is in order. A reflexive look toward the multidisciplinary nature of such HAT projects illuminates the need for a deeper dive into varied stakeholder considerations of ethics and trust. In this paper, we investigate the impact of domain---and the ranges of expertise within domains---on ethics- and trust-related considerations for HATs in mental health. We outline our engagement of 23 participants in two speculative activities: design fiction and factorial survey vignettes. Grounded by a video storyboard prototype, AI- and Psychotherapy-domain experts and novices alike imagined TEAMMAIT, a prospective AI system for psychotherapy training. From our inductive analysis emerged 10 themes surrounding ethics, trust, and collaboration. Three can be seen as substantial barriers to trust and collaboration, where participants imagined they would not work with an AI teammate that didn't meet these ethical standards. Another five of the themes can be seen as interrelated, context-dependent, and variable factors of trust that impact collaboration with an AI teammate. The final two themes represent more explicit engagement with the prospective role of an AI teammate in psychotherapy training practices. We conclude by evaluating our findings through the lens of Mayer et al.'s Integrative Model of Organizational Trust to discuss the risks of HATs and adapt models of ability-, benevolence-, and integrity-based trust. These updates motivate implications for the design and integration of HATs in mental health work.

Informal caregivers perform an important role in taking care of family members with chronic disease. Informal caregivers' mental health can be negatively impacted by life-changing events (e.g., patients' diagnosis, care transitioning, etc.). This leads the caregiver to suffer from interpersonal and intrapersonal conflicts, causing a sense of disorientation and escalating malaise. In this study, we investigated informal caregivers' experiences of facing conflicts and life-changing events by qualitatively analyzing the data from online health communities. We categorized conflicts using a psychodynamic framework. We further looked at the interplay of life-changing events and conflicts and how this leads to caregivers' sense-making and decisions to mediate conflicts. We also found that online health communities provide support by helping caregivers interpret and navigate conflicts and raising awareness of the temporal resolution of life-changing events. We conclude this study by discussing designing online health communities to better support such practice.

This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a supposedly "debiased" embedding. These biases are concerning in light of the widespread use of word embeddings. The associations are identified by geometric patterns in word embeddings that run parallel between people's names and common lower-case tokens. The algorithm is highly unsupervised: it does not even require the sensitive features to be pre-specified. This is desirable because: (a) many forms of discrimination?such as racial discrimination-are linked to social constructs that may vary depending on the context, rather than to categories with fixed definitions; and (b) it makes it easier to identify biases against intersectional groups, which depend on combinations of sensitive features. The inputs to our algorithm are a list of target tokens, e.g. names, and a word embedding. It outputs a number of Word Embedding Association Tests (WEATs) that capture various biases present in the data. We illustrate the utility of our approach on publicly available word embeddings and lists of names, and evaluate its output using crowdsourcing. We also show how removing names may not remove potential proxy bias.

While humor is often thought to be beyond the reach of Natural Language Processing, we show that several aspects of single-word humor correlate with simple linear directions in Word Embeddings. In particular: (a) the word vectors capture multiple aspects discussed in humor theories from various disciplines; (b) each individual’s sense of humor can be represented by a vector, which can predict differences in people’s senses of humor on new, unrated, words; and (c) upon clustering humor ratings of multiple demographic groups, different humor preferences emerge across the different groups. Humor ratings are taken from the work of Engelthaler and Hills (2017) as well as from an original crowdsourcing study of 120,000 words. Our dataset further includes annotations for the theoretically-motivated humor features we identify.