Constance and Martin Silver Center on Data Science and Social Equity

o Data systems such as “big data” (large, unstructured collections of data high in volume,  variety, or velocity) 

o Data visualization 

o Efficient processing of unstructured data 

o Artificial intelligence (including an anti-racist and equitable approach to A.I., queer A.I., “emancipatory A.I.”) 

o Deep learning (neural networks, etc.) 

o Machine learning and other predictive modeling (including identifying and ameliorating racial  bias in machine learning algorithms) 

o Machine perception and sensing 

o Natural language processing 

o Translational data science 

o Geospatial computation

o The ethics of data science 

o Data science with human service populations 

o Integration of data science with digital technologies 

o Development of data-driven apps to address significant social problems

Principal Investigators: Dr. Nicholas Lanzieri, Clinical Associate Professor and Dr. Anne C. Dempsey, Clinical Associate Professor, NYU Silver School of Social Work

Collaborators: Shivani Dhir, Dr. Julian Togelius, Dr. Jan Plass, and Jeff Brenneman

Dates of award: 9/1/2023 – 8/31/2024

Amount of award: $77,000

Schools of Social Work are increasingly using technology-based simulations to train students in practice-related skills, as agency-based practicums become more restrictive, and new research shows the benefits of social work education simulation for students. This newly funded study aims to develop and pilot test a technology-based simulation template for social work students in collaboration with faculty from the Tandon School of Engineering and Steinhardt School of Culture, Education, and Human Development. The template will contain a simulation scenario based on the research findings of Silver scholars, support contemporary practice skill development, and be assessed for effectiveness and feasibility for dissemination in a pilot study with MSW students.

Principal Investigator: Dr. Neil Guterman, Professor, NYU Silver School of Social Work

Collaborators: Dr. Jennifer Bellamy, Dr. Aaron Banman, and Dr. Justin Harty

Dates of award: 9/21/2022 – 8/31/2023

Amount of award: $20,000

Study description: 

Parents’ early verbal engagement in the home is essential to young children’s cognitive development, learning preparedness, and healthy psychosocial development. While much is known about the role of mother-infant interactions in the home, the role that fathers play in the well-being of their young children is understudied. This research project will employ a highly innovative language analysis technology guided by artificial intelligence-based models to analyze over 3,000 hours of audio-recorded interactions between parents and babies, with verbal and self-reported data from biological fathers and mothers in a predominantly Latinx and African American sample of families living in the greater Chicago metropolitan area.  Analyses will examine father-child as well as mother-child interactions (e.g., word counts, vocalizations, conversational turns) and explore how these interactions are linked with and predict such factors as the quality of the mother-father relationship, the attainment of the child’s developmental milestones, and physical child abuse and neglect risk. Findings from this study will lay the groundwork for larger research proposals to apply data science methods that explore the role of fathers in early childhood development and help predict risk of child abuse and neglect.

Principal Investigator: Dr. Michelle Munson, Professor, NYU Silver School of Social Work

Collaborators: Dr. Sadiq Patel (Harvard University), Dr. Molly Finnerty (NYU Grossman School of Medicine/New York State Office of Mental Health), Dr. Deborah Layman (New York State Office of Mental Health/Research Foundation for Mental Hygiene), Qingxian Chen (New York State Office of Mental Health)

Dates of award: 9/1/2022 – 8/31/2023

Amount of award: $70,000

Study description: 

The Covid-19 pandemic laid bare gaps in our healthcare system, and young adult behavioral health is among our most challenging crises. When there is unequal availability and utilization of mental health services in communities, there will be great divides in life outcomes. Support for this project will catapult a team from the Silver School of Social Work, the Grossman School of Medicine and the New York State Office of Mental Health (NYSOMH) who together will harness ‘big data’ to begin to address the unmet mental health need among young adults. Specifically, the project will leverage the PSYCKES platform’s large integrated mental health and Medicaid claims database, to identify ‘hotspot’ communities of need, where there are high rates of young adults with serious mental illness and low levels of utilization of professional services. Our project will use both statistical and machine learning methods to identify ‘drivers’ of mental health care. Findings will inform future research to reduce social inequities among some of New York’s most disadvantaged citizens. To that end, our team will use project findings as the groundwork for grant applications in partnership with the emergent communities, and to advance consumer- facing technologies such as ‘MyCHOIS’, a system that provides direct access and messaging for patients to their health information and real-time resources in moments of need. Finally, results will inform state leadership in their policy and program efforts to address gaps in services.

Principal Investigator: Dr. Ernest Gonzales, Associate Professor and MSW Program Director, NYU Silver School of Social Work

Collaborators: Dr. Yi Wang, Dr. Forrest Bao, Cliff Whetung, and Natalie Green

Dates of award: 3/23/2022 – 2/28/2023

Amount of award: $10,000. Dean's Research Fund and C+M Silver Center

Study description: 

Cognitive impairment is a worldwide epidemic and its effects are borne disproportionately by minoritized groups in the United States. Yet, nearly a third of all dementia cases can be prevented and equity is within reach. Longitudinal and experimental studies have identified important predictors to bolster cognitive functioning and brain structure. Machine learning is a novel statistical method that has rarely been utilized with predicting cognitive functioning in later life. While this method holds tremendous promise to interrogate and confirm existing theory, there are also significant ethical and methodological concerns that arise within the context of structural racism. Utilizing 14 years of data from a large representative sample of 15,385 older adult respondents to the Health and Retirement Study (2006-2020), and guided by minority stress theory, this study will compare and contrast traditional statistical approaches with that of machine learning to examine risk and protective factors to cognitive health. The findings from this study will inform methodological innovations to better understand cognitive impairment and socio-environmental factors, and will contribute to the development of theory and knowledge to inform health care policy and practices.

Principal Investigator: Dr. Victoria Stanhope (PI), Professor, NYU Silver School of Social Work.

Collaborators: Dr. Elizabeth Matthews, Dr. Sarah Shugars

Dates of award: 9/1/2021 – 8/31/2022

Amount of award: $70,500

Study description: Service disengagement is a persistent and widespread problem within the mental health system. One solution for the problem of service disengagement is to deliver person-centered care (PCC), which ensures that care is individualized and service users are active empowered partners in their treatment. This study will use an innovative artificial intelligence approach to examine Collaborative Documentation, a strategy to promote PCC in behavioral health clinics in which clinicians complete visit notes jointly with consumers during the session. The study will use natural language processing, a text mining technique that translates narrative text to structured data using an algorithm to analyze clinical visit notes. This research study will contribute to the evidence base on Collaborative Documentation and develop an algorithm to analyze PCC to inform quality improvement in behavioral health care.

Principal Investigator: Dr. Doris F. Chang, Associate Professor, NYU Silver School of Social Work.

Collaborators: Dr. Sumie Okazaki, Dr. Thu T. Nguyen, Dr. Maureen Craig

Dates of award: 9/1/2021 – 8/31/2022

Amount of award: $56,000

Study description: Anti-Asian violence and harassment have escalated during the Covid-19 pandemic, catalyzed by the racial framing of the virus, and converging with a national awakening to systematic racism following the death of George Floyd. Consistent with prior research on racism and mental health, Covid-related discrimination is associated with poorer mental health outcomes in diverse Asian American samples (Cheah et al., 2021; Stop AAPI Hate Mental Health Report, 2021). However, studies rarely consider how macro-contextual factors such as ambient racial climate (including negative views of other racial groups) and community characteristics affect racialized individuals’ psychosocial experiences, intergroup relations, and collective actions aimed at addressing racial inequality. The main aim of this study is to examine how regional variations in racial climate (as indicated by sentiment analysis of geocoded Twitter data of anti-Asian and anti-Black bias as well as solidarity and allyship across racial groups) are associated with three sets of outcomes: a) racial discrimination and mental  health, b) intergroup attitudes (structural awareness, sense of belonging, political commonality/coalitional attitudes), and c) collective action and coalitional support (own-group benevolent support and political activism, Asian-Black allyship behaviors). Taking into account the diverse immigration histories and discrimination experiences of these groups, analyses will determine how regional public discourse about race affects well-being, intergroup attitudes, and collective action. The study will also examine how regional variations in residential segregation/integration and income inequality reflect community contexts for intergroup conflict, cooperation and competition (Tajfel, 1982), and may be associated with the same three sets of outcomes. Understanding the multi-level factors that shape Asian Americans’ individual and intergroup responses to racism, and subsequent civic and political engagement has important implications for community well-being and intergroup solidarity, and shaping a more inclusive, equitable, and democratic society.