A Shoulder to Cry on: Towards A Motivational Virtual Assistant for Assuaging Mental Agony

Abstract

Mental Health Disorders continue plaguing humans worldwide. Aggravating this situation is the severe shortage of qualified and competent mental health professionals (MHPs), which underlines the need for developing Virtual Assistants (VAs) that can assist MHPs. The data+ML for automation can come from platforms that allow visiting and posting messages in peerto-peer anonymous manner for sharing their experiences (frequently stigmatized) and seeking support. In this paper, we propose a VA that can act as the first point of contact and comfort for mental health patients. We curate a dataset, Motivational VA: MotiVAte comprising of 7k dyadic conversations collected from a peer-topeer support platform. The system employs two mechanisms: (i) Mental Illness Classification: an attention based BERT classifier that outputs the mental disorder category out of the 4 categories, viz., Major Depressive Disorder (MDD), Anxiety, Obsessive Compulsive Disorder (OCD) and Post-traumatic Stress Disorder (PTSD), based on the input ongoing dialog between the support seeker and the VA; and (ii) Mental Illness Conditioned Motivational Dialogue Generation (MI-MDG): a sentiment driven Reinforcement Learning (RL) based motivational response generator. The empirical evaluation demonstrates the system capability by way of outperforming several baselines.

A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures

“…Prior work has illustrated the importance of trust for continued voice assistant use [31,35], as trust is pivotal to user adoption of voice assistants [33,45] and willingness to broaden the scope of voice assistant tasks [27]. It is especially important to support trust-building between users and voice assistants as researchers continue to imagine and develop new capabilities for them, including complex tasks such as supporting healthcare tasks [41,55], giving mental health advice [52,66], and other high stakes decision-making [17].…”

“…Within the past five years, advancements in NLP have achieved huge gains in accuracy when tested against standard datasets [8,18,34,56,58,60,63], with state-ofthe-art accuracy in natural language processing models as high as 99% for certain tasks [8,34]. This has led many practitioners and researchers alike to imagine a near future where voice assistants can be used in increasingly complex ways, including supporting healthcare tasks [41,55], giving mental health advice [52,66], and high stakes decision-making [17].…”

An “Integrative Survey on Mental Health Conversational Agents to Bridge Computer Science and Medical Perspectives”

“…Most of the papers ( 43%) we reviewed do not deal with a specific mental health condition but work towards general mental health well-being (Saha et al, 2022a). The methods proposed in such papers are applicable to the symptoms associated with a broad range of mental health issues (e.g.…”

“…An advantage of the models proposed in these papers is that they could potentially offer support to a broad group of users irrespective of the underlying mental health condition. Papers without a target demographic and a target mental health category focus on proposing methods such as using generative language models for psychotherapy (Das et al, 2022a), or to address specific modules of the CAs such as leveraging reinforcement learning for response generation (Saha et al, 2022b).…”

“…The NLP community is actively exploring the role of generative LLMs (e.g. GPT-4) in designing CAs including mental healthcare-related CAs (Das et al, 2022a;Saha et al, 2022b;Yan and Nakashole, 2021). With the advent of more sophisticated LLMs, fluency, repetitions and, ungrammatical formations are no longer concerns for dialogue generation.…”