The intersection of data visualization and human-robot interaction (HRI) is a burgeoning field. Understanding, communicating, and processing different kinds of data for creating versatile visualizations can benefit HRI. Conversely, expressing different kinds of data generated from HRI through effective visualizations can provide interesting insights. Our work adds to the literature of this growing domain. In this paper, we present our exploratory work on visualizing mental health data on a social robot. Particularly, we discuss development of mental health data visualizations using a participatory design (PD) approach. As a first step with mental health data visualization on a social robot, this work paves the way for relevant further work and using social robots as data visualization tools.

Social robots have been used to assist with mental well-being in various ways such as to help children with autism improve on their social skills and executive functioning such as joint attention and bodily awareness. They are also used to help older adults by reducing feelings of isolation and loneliness, as well as supporting mental well-being of teens and children. However, existing work in this sphere has only shown support for mental health through social robots by responding interactively to human activity to help them learn relevant skills. We hypothesize that humans can also get help from social robots in mental well-being by releasing or sharing their mental health data with the social robots. In this paper, we present a human-robot interaction (HRI) study to evaluate this hypothesis. During the five-day study, a total of fifty-five (n=55) participants shared their in-the-moment mood and stress levels with a social robot. We saw a majority of positive results indicating it is worth conducting future work in this direction, and the potential of social robots to largely support mental well-being.

In late December 2019, the novel coronavirus (Sars-Cov-2) and the resulting disease COVID-19 were first identified in Wuhan China. The disease slipped through containment measures, with the first known case in the United States being identified on January 20th, 2020. In this paper, we utilize survey data from the Inter-university Consortium for Political and Social Research and apply several statistical and machine learning models and techniques such as Decision Trees, Multinomial Logistic Regression, Naive Bayes, k-Nearest Neighbors, Support Vector Machines, Neural Networks, Random Forests, Gradient Tree Boosting, XGBoost, CatBoost, LightGBM, Synthetic Minority Oversampling, and Chi-Squared Test to analyze the impacts the COVID-19 pandemic has had on the mental health of frontline workers in the United States. Through the interpretation of the many models applied to the mental health survey data, we have concluded that the most important factor in predicting the mental health decline of a frontline worker is the healthcare role the individual is in (Nurse, Emergency Room Staff, Surgeon, etc.), followed by the amount of sleep the individual has had in the last week, the amount of COVID-19 related news an individual has consumed on average in a day, the age of the worker, and the usage of alcohol and cannabis.

The impact of digital technologies on those with mental health treatment histories is rarely addressed by sweeping reports and recommendations that focus on the impacts of technology on society. In a paper submitted to the Australian Human Rights Commission about promoting fair and equitable deployments of Artificial Intelligence, Piers Gooding addressed this gap. His report showed how infringements on privacy through data collection pose risks to people with disabilities and mental health service-users. Digital technologies and artificial intelligence-enabled changes to the provision of mental health services are ubiquitous today, facilitating'supported decision-making' in healthcare services, peer networking, face-to-face support, and crisis support. They are often instrumental in monitoring abuses in care provision too.