Stress is considered to be a modern day "global epidemic"; so given the widespread nature of this problem, it would be beneficial if solutions that help people to learn how to cope better with stress were scalable beyond what individual or group therapies can provide today. Therefore, in this work, we study the potential of smart-phones as a pervasive medium to provide "crowd therapy". The work melds two novel contributions: first, a microintervention authoring process that focuses on repurposing popular web applications as stress management interventions; and second, a machine-learning based intervention recommender system that learns how to match interventions to individuals and their temporal circumstances over time. After four weeks, participants in our user study reported higher self-awareness of stress, lower depression-related symptoms and having learned new simple ways to deal with stress. Furthermore, participants receiving the machine-learning recommendations without option to select different ones showed a tendency towards using more constructive coping behaviors.

Figure 1: Existing videoconferencing platforms such as Microsoft Teams provide limited audience feedback when giving presentations (left). We develop AffectiveSpotlight which analyzes and spotlights audience members in real-time to support presenters (right). Text boxes indicate the main components of the platforms.

The delivery of mental health interventions via ubiquitous devices has shown much promise. A conversational chatbot is a promising oracle for delivering appropriate just-intime interventions. However, designing emotionally-aware agents, specially in this context, is under-explored. Furthermore, the feasibility of automating the delivery of just-in-time mHealth interventions via such an agent has not been fully studied. In this paper, we present the design and evaluation of EMMA (EMotion-Aware mHealth Agent) through a two-week long human-subject experiment with N=39 participants. EMMA provides emotionally appropriate micro-activities in an empathetic manner. We show that the system can be extended to detect a user's mood purely from smartphone sensor data. Our results show that our personalized machine learning model was perceived as likable via self-reports of emotion from users. Finally, we provide a set of guidelines for the design of emotion-aware bots for mHealth.

Abstract-Behavior modification in health is difficult, as habitual behaviors are extremely well-learned, by definition. This research is focused on building a persuasive system for behavior modification around emotional eating. In this paper, we make strides towards building a just-in-time support system for emotional eating in three user studies. The first two studies involved participants using a custom mobile phone application for tracking emotions, food, and receiving interventions. We found lots of individual differences in emotional eating behaviors and that most participants wanted personalized interventions, rather than a pre-determined intervention. Finally, we also designed a novel, wearable sensor system for detecting emotions using a machine learning approach. This system consisted of physiological sensors which were placed into women's brassieres. We tested the sensing system and found positive results for emotion detection in this mobile, wearable system.

Parenting is always demanding, but families coping with neurodevelopmental disorders, such as ADHD, experience unique challenges. To address these challenges, research in the area of Parental Behavioral Therapy is accelerating. This type of therapy focuses on behavioral strategies that, if practiced regularly, can have a positive impact on the child's long-term behavior, as well as a reduction in parental stress. While these strategies are simple, there are hurdles to putting them into practice. First, parents often struggle with their own-often-undiagnosed-mental health challenges. Second, due to the needs of their children, parents are under immense stress in addition to regular, daily life stresses. Our work explores how to monitor parental stress and offers in situ support to remind parents of behavioral strategies to practice in moments of duress. We gained insight into how to design for the dynamics of families with ADHD children by using a prototype of our system as a probe. Our goal was to bring to the forefront simple strategies that can positively impact family ties and enhance the wellbeing of the child. We present results that suggest that when interventions are cued during moments of duress, technology might prove useful in supporting behavioral therapy.