Berkeley Public Health students join new cohort of Computational Social Science fellows

The Berkeley Computational Social Science Training Program (CSSTP) is delighted to welcome its second cohort of new fellows for the fall 2021 semester at UC Berkeley. The CSSTP is a two-year multidisciplinary training program in advanced data analytics for predoctoral students in the social and behavioral sciences. This year’s cohort represents students from Berkeley’s Department of Sociology, and Schools of Social Welfare and Public Health, including Epidemiology and Biostatistics, and the Health Policy Program. These new fellows join last year’s cohort, who launched the program in 2020.

Benjamin Fields is a PhD student in Sociology at UC Berkeley. A health-oriented social scientist, he wants to focus his research on a social understanding of diet and its relationship to well-being, looking beyond the physiological definition of food towards one that includes social, cultural, political, and economic considerations. “The Computational Social Science Training Program will develop me to lead the next revolution of research through big-data and geospatial oriented approaches. Research was not able to benefit as much from the agricultural or industrial revolutions, but I believe that the digital revolution will influence our ability to understand the world beyond what we can currently comprehend.”

Daniel Lobo is also a PhD student in Sociology at UC Berkeley. Historically, his research interests have been in education inequality in K-12 and higher education, with a focus on the life outcomes of low-income students. Lobo is currently interested in two lines of research: the global political economy of higher education and the effects of social media on cultural production and reproduction. Epistemologically, he seeks to leverage big data and machine learning to bridge disciplines in his research and to ask predictive questions in the social sciences. “As a CSSTP fellow, I look forward to learning about the ethics of computational methods, developing my quantitative skillset under the mentorship of Berkeley data science faculty, and being in fellowship with a diverse, talented group of interdisciplinary peers.” Outside of the academy, he enjoys mentoring first-generation, low-income students of color. Lobo identifies as Black, queer, and working class. He holds a BA in Social Studies, with high honors, from Harvard College.

Krista Neumann is a PhD student in Epidemiology at Berkeley’s School of Public Health. Her goal is to apply her training in Mathematics to social epidemiological questions focused on reducing health disparities. Neumann’s current research interests aim to answer the causal question: which policies, programs and interventions most successfully reduce systematically embedded barriers to health for marginalized and low-income communities. She’s particularly interested in food and nutrition insecurity as a specific outcome, as well as ways to overcome obstacles which prevent evidence from affecting meaningful policy changes. Neumann holds a Bachelors of Mathematics from the University of Waterloo in Canada. “I’m thrilled to be joining such an exceptional cadre of CSSTP fellows! The program’s interdisciplinary and integrated approach offers a unique opportunity to collaborate with and learn from others focused on bridging computational methods and social science frameworks to further health equity. I’m excited to build up my quantitative and methodological toolkits to better support my goals.”

Valentín “Val” Sierra is a PhD student at Berkeley’s School of Social Welfare with a designated emphasis in Global Metropolitan Studies. They hold a MSW from Berkeley’s School of Social Welfare and a BA in Native American Studies, with highest honors, from UC Davis. Their clinical and research agendas focus on eliminating mental health disparities, particularly suicide and depression, for urban Native American young people through culturally grounded practices and interventions. Sierra is an Associate Clinical Social Worker and an active member of the California Yaqui (Yoeme) Indian community. “I am excited to engage in a multidisciplinary learning community through the CSSTP and gain advanced training in data analytic techniques,” says Sierra. “I look forward to applying this knowledge to structure research as a decolonial tool to serve my community in the continued pursuit towards health equity and justice.”

Solis Winters is a PhD student in Health Policy, with a specialization in Population Health and Data Science, at Berkeley’s School of Public Health. Her research focuses on improving health and nutrition during the first 1000 days of life, from pregnancy through age two. She is especially interested in using methods from causal inference to better understand what types of community-based interventions can improve birth outcomes and child malnutrition in low-income communities. “I am excited to join a program that recognizes the need for cross-disciplinary methods and perspectives in improving health outcomes and achieving health equity,” says Winters. “Through the CSSTP, I hope to learn how advanced computational methods from machine learning and causal inference can be incorporated into my own research and translated into effective, evidence-based programs and policies to improve maternal and child health.”

Funded by a grant from the NIH National Institute of Child Health & Human Development, this two-year program is led by BIDS Faculty Affiliate David Harding, a professor of Sociology and faculty director of the Berkeley Social Science Data Laboratory (D-Lab); BIDS Faculty Affiliate Maya Petersen, MD, PhD, chair of the Division of Biostatistics at the Berkeley School of Public Health; and Tim Thomas, BIDS Research Training Lead for the Computational Social Science Training Program, and Research Director of Berkeley’s Urban Displacement Project at IGS & CCI.

PI David Harding is enthusiastic in welcoming this year’s cohort: “We’re delighted to welcome this talented and accomplished group of scholars to the Computational Social Science Training Program. Their work in the program will combine data analytic tools and domain knowledge to advance research in health equity and address structural inequalities.”

According to Research Training Lead Tim Thomas, “It’s exciting to see this talented and diverse group of students take part in the important merge of social and data science. We are less likely to break orbit in new population research without interdisciplinary approaches and voices using data science tools and domain knowledge to inform important research questions.”

The new cohort will begin their fellowships this fall.