Interventions for Serious Mental Illnesses
Financial Technologies (FinTech) for Mental Health
The relationship between mental health and financial difficulties is complex. Those living with mental illnesses are at increased risk of financial hardships and debt-related stress. This can be further complicated by a range of problematic financial behaviors related to specific mental health symptoms, such as impulsive purchasing or missing deadlines. While previous studies have resulted in valuable insights on how mental health symptoms can manifest in specific financial behaviors, they might not lead to the complete picture given their reliance on self-reported perceptions of individual’s own behaviors. In other words, self-reported data can suffer from incomplete recall and other biases, particularly during symptomatic periods. Being able to access objective personal financial data can help to address this issue. Recent increased digitization of banking services have made fine grained personal financial data more accessible than ever before. By leveraging this objective financial data, we can more easily investigate this relationship — the ebb and flow of finances and mental health.
Collaboration with: Dr. Thomas Richardson (University of Southampton, UK), Dr. Mark Matthews (Trinity College, Dublin), Dr. Dahlia Mukherjee and Dr. Erika Saunders (Dept. of Psychiatry at Penn State College of Medicine)
Related Publications:
The relationship between mental health and financial difficulties is complex. Those living with mental illnesses are at increased risk of financial hardships and debt-related stress. This can be further complicated by a range of problematic financial behaviors related to specific mental health symptoms, such as impulsive purchasing or missing deadlines. While previous studies have resulted in valuable insights on how mental health symptoms can manifest in specific financial behaviors, they might not lead to the complete picture given their reliance on self-reported perceptions of individual’s own behaviors. In other words, self-reported data can suffer from incomplete recall and other biases, particularly during symptomatic periods. Being able to access objective personal financial data can help to address this issue. Recent increased digitization of banking services have made fine grained personal financial data more accessible than ever before. By leveraging this objective financial data, we can more easily investigate this relationship — the ebb and flow of finances and mental health.
- Case study and prospective paper to explore and lay out future research priorities for this emerging domain
- Large-scale international survey to explore debt, online financial ecosystems, and symptomatic spending behaviors/motivations for individuals with bipolar disorder
- Evaluation study of a financial intervention system prototype with patients and care partners, with a focus on their ideal balance of privacy/autonomy concerns vs. the potential for financial harm reduction
Collaboration with: Dr. Thomas Richardson (University of Southampton, UK), Dr. Mark Matthews (Trinity College, Dublin), Dr. Dahlia Mukherjee and Dr. Erika Saunders (Dept. of Psychiatry at Penn State College of Medicine)
Related Publications:
- Financial Data Sharing Preferences to Support Longitudinal Care Management. (currently under review).
- Blair, J., Brozena, J., Matthews, M., Richardson, T., & Abdullah, S. (2022). Financial technologies (FinTech) for mental health: The potential of objective financial data to better understand the relationships between financial behavior and mental health. Front. Psychiatry 13:810057.
- Initial prototype---AI Money Minder (AIMM): a Fintech platform that helps identify personalized early-warning signs in financial data from individuals with serious mental illness---as part of Penn State's Nittany AI Challenge
**View our initial survey findings presented as poster at CHI 2023 "Supportive Data Driven Financial Technologies for Individuals with Serious Mental Illnesses" (pdf below)
chi_23_poster.pdf | |
File Size: | 506 kb |
File Type: |
Predicting Relapse Onset in Bipolar Disorder from Online Behavioral Data
Bipolar disorder (BD) has been recognized as one of the ten most debilitating illnesses and is associated with poor functional and clinical outcomes. Cyclical manic and depressive episodes are often accompanied by behavioral anomalies and significant changes in social interactions: hyperactivity, decreased need of sleep, being more talkative, and irritability often preceding mania and symptoms including low energy, hypersomnia, and lack of interest are common leading into and throughout depressive episodes. At the same time, our social relationships and behavioral routines are now often embedded in online activities, such as social interactions via email or networking sites, work productivity, information searches, and online shopping. The same holds true for individuals with serious mental illnesses like BD, and thus could be used to identify early-warning signs.
The primary purpose of this study is to assess the acceptability and feasibility of using the online behavioral data of individuals with BD to predict relapse onset. Specifically, data from Google, Facebook, and Twitter is used to understand online behavior trends of patients with BD. Additionally, this work addresses the user’s perspective on using personal data for this purpose, the perceived utility, and future design. Our long-term goal is to develop a computational framework that can identify behavioral anomalies and early-warning signs in patients with BD using online data.
Collaboration with: Dr. Dahlia Mukherjee and Dr. Erika Saunders -- Dept. of Psychiatry at Penn State College of Medicine
Related Publications:
Bipolar disorder (BD) has been recognized as one of the ten most debilitating illnesses and is associated with poor functional and clinical outcomes. Cyclical manic and depressive episodes are often accompanied by behavioral anomalies and significant changes in social interactions: hyperactivity, decreased need of sleep, being more talkative, and irritability often preceding mania and symptoms including low energy, hypersomnia, and lack of interest are common leading into and throughout depressive episodes. At the same time, our social relationships and behavioral routines are now often embedded in online activities, such as social interactions via email or networking sites, work productivity, information searches, and online shopping. The same holds true for individuals with serious mental illnesses like BD, and thus could be used to identify early-warning signs.
The primary purpose of this study is to assess the acceptability and feasibility of using the online behavioral data of individuals with BD to predict relapse onset. Specifically, data from Google, Facebook, and Twitter is used to understand online behavior trends of patients with BD. Additionally, this work addresses the user’s perspective on using personal data for this purpose, the perceived utility, and future design. Our long-term goal is to develop a computational framework that can identify behavioral anomalies and early-warning signs in patients with BD using online data.
Collaboration with: Dr. Dahlia Mukherjee and Dr. Erika Saunders -- Dept. of Psychiatry at Penn State College of Medicine
Related Publications:
- Blair, J., Mukherjee, D., Saunders, E.F.H. & Abdullah, S. (2022). Knowing how long a storm might last makes it easier to weather: Exploring needs and attitudes toward a data-driven and preemptive intervention system for bipolar disorder. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23), April 23–28, 2023, Hamburg, Germany. ACM.
- Blair, J. (2021). Designing for serious mental illnesses: Enabling early detection and supporting financial wellbeing in bipolar disorder. In Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers (UbiComp-ISWC ’21 Adjunct).
- Blair, J., Mukherjee, D., Saunders, E.F.H., & Abdullah, S. (2020). Opportunities for Collaborative Clinical Work: Predicting Relapse Onset in Bipolar Disorder from Online Behavior. In14th EAI International Conference on Pervasive Computing Technologies for Healthcare (Pervasive-Health ’20) .
Social Media Mental Health
Mental Health Discourse on Twitter: A Study of Essential Workers During Covid-19
The recent Covid-19 pandemic has had a significant impact on mental health and wellbeing, leading to large-scale lifestyle change, social isolation, and high stress. This has been especially pertinent to essential workers—from those in the medical field treating patients to those in retail supply chains meeting the needs of everyday life. In this work, we aim to understand some of the key issues related to mental health and wellbeing of essential workers during the Covid-19 pandemic and the role technology and social media can play.
To do so, we take a two-pronged approach. By analyzing essential workers’ Twitter posts from a large-scale data set, we map out trends over the course of the pandemic, both for frequency and content, as well as a comparison of mental health discourse before and during the pandemic. Additionally, we conduct interviews with a range of essential workers to study their first-hand experiences and the effects the pandemic has had on their social isolation, stress, and mental wellbeing at a greater depth, as well as their current coping strategies and how they have continued to remotely maintain their social support networks during this time. Based on this insight, we identify challenges for existing technologies and key points where technology can better help support their needs related to mental wellbeing.
In-collaboration with Dr. Huang and the Crowd-AI Lab at Penn State IST
The recent Covid-19 pandemic has had a significant impact on mental health and wellbeing, leading to large-scale lifestyle change, social isolation, and high stress. This has been especially pertinent to essential workers—from those in the medical field treating patients to those in retail supply chains meeting the needs of everyday life. In this work, we aim to understand some of the key issues related to mental health and wellbeing of essential workers during the Covid-19 pandemic and the role technology and social media can play.
To do so, we take a two-pronged approach. By analyzing essential workers’ Twitter posts from a large-scale data set, we map out trends over the course of the pandemic, both for frequency and content, as well as a comparison of mental health discourse before and during the pandemic. Additionally, we conduct interviews with a range of essential workers to study their first-hand experiences and the effects the pandemic has had on their social isolation, stress, and mental wellbeing at a greater depth, as well as their current coping strategies and how they have continued to remotely maintain their social support networks during this time. Based on this insight, we identify challenges for existing technologies and key points where technology can better help support their needs related to mental wellbeing.
In-collaboration with Dr. Huang and the Crowd-AI Lab at Penn State IST
- Blair, J., Hsu, C.Y., Qiu, L., Huang, S.H., Huang, T.H.K., & Abdullah, S. (2021). Using Tweets to Assess Mental Well-being of Essential Workers During the COVID-19 Pandemic. In CHI Conference on Human Factors in Computing Systems Extended Abstracts (CHI’21 Extended Abstracts), May 8–13, 2021, Yokohama, Japan. ACM.
- Watch the video presentation of this work from CHI 2021.
- Featured post on Penn State Social Science Research Institute's Insights from Experts Blog "Are Essential Workers More Optimistic Online? Using Tweets to Assess Mental Well-being of Essential Workers During the Covid-19 Pandemic"
Supporting Constructive Mental Health Discourse on Instagram
Previous research has focused on the social practices and interactions of those who choose to share their mental health experiences with others on public social media platforms. Despite the negativity and stigma users often face, the trade-off in favor of social support, community building, and combating that stigma still prevails. Work has been conducted to understand what users are willing to disclose, how people share their stories, and why, based on the public-facing content they produce. However, less is known about how users view and rationalize their own disclosure choices and why they believe they share, as compared to the researcher's own interpretation. By interviewing active Instagram users, this work also intends to address how well users believe existing technical features and affordances align with their own needs and what this user insight can mean for building more beneficial social support systems for specific user groups.
Previous research has focused on the social practices and interactions of those who choose to share their mental health experiences with others on public social media platforms. Despite the negativity and stigma users often face, the trade-off in favor of social support, community building, and combating that stigma still prevails. Work has been conducted to understand what users are willing to disclose, how people share their stories, and why, based on the public-facing content they produce. However, less is known about how users view and rationalize their own disclosure choices and why they believe they share, as compared to the researcher's own interpretation. By interviewing active Instagram users, this work also intends to address how well users believe existing technical features and affordances align with their own needs and what this user insight can mean for building more beneficial social support systems for specific user groups.
- Blair, J. & Abdullah, S. (2018). Supporting Constructive Mental Health Discourse in Social Media. In PervasiveHealth ’18: 12th EAI International Conference on Pervasive Computing Technologies for Healthcare. May 21–24, 2018, New York, NY, USA.