Introduction to Computational Social Science
Instructor: Yongjun Zhang
Dates: July 15 – July 19, 2023
Course Description
The rapid development in information and communications technology has revolutionized how social scientists think about human and social behavior and conduct social research. Especially during the COVID-19 pandemic, big tech firms have provided scholars with various large-scale structured and unstructured datasets. Thus, scholars need to build new toolkits to process text, image, audio, video, and geospatial data innovatively and efficiently in order to advance social theories and address social science problems. This course aims to 1) offer a survey of methods and techniques commonly used in computational social science and 2) introduce a pipeline of doing computational social science in different settings such as cloud computing. Topics in the course consist of research ethics in the big data era, basics in machine learning (including deep learning), basics in cloud computing, natural language processing, basics in computer vision, APIs and web-scraping, and data visualization. The programming language used in the course includes R and Python (Students with limited programming language are also encouraged to apply, and we will provide lab training.).
Prerequisites:
- Basic programming skills in R or Python.
- Intro statistics and linear regression models.
About the Instructor
Yongjun Zhang is an Assistant Professor of Sociology and Institute for Advanced Computational Science at the State University of New York (Stony Brook). He is also a research affiliate at New York University. Dr. Zhang is a computational sociologist who combines computational, network, and statistical methods with large-scale datasets to study organizational, social, and political behavior, particularly focusing on segregation and polarization in different settings. Currently, he is using relational data from SafeGraph and Facebook as well as 190 million L2 voter records and 260 million Infutor consumer records to assess the antecedents and consequences of racial/partisan/income segregation in the United States. He is also using deep learning methods to detect and monitor anti-AAPI hate speech on Twitter since the COVID-19 outbreak. His research has been funded by OVPR and IACS seed grants at Stony Brook University. His work has appeared in leading social science journals such as the American Journal of Sociology, Demography, Journal of Marriage and Family, and Plos One, among others. He has won the 2020 James Coleman Award from the Sociology of Education Section at American Sociological Association and the 2021 SIM Best Paper Submission at the Academy of Management.