Spring 2023 - 60500 - PA 397C - Advanced Empirical Methods for Policy Analysis

COMPUTATIONAL SOCIAL SCIENCE METHODS

Course description: https://css.jima.me/

This course introduces computational social science methods and contextualizes these methods within social science research design. The first part of this course (w1–w3) gives you an overview of this course, programming fundamentals, and how to use high-performance cloud computing resources. The second part (w4–w12) is analysis-oriented and primarily covers text analysis (w4–w8; with an emphasis on multilingual language analysis) and network analysis (w9–w12). The last few weeks focus on research design with computational methods and the final project. Bilingual or multilingual language ability is a plus. Programming is an essential part of this course but not the purpose and will not be taught. We will be coding for social good.

The course has demanding prerequisites; therefore, you probably need to work on the prerequisites in 2022 summer and fall if you are highly motivated. All registrations need to be approved by the instructor in late 2022 fall. You can join the learning group where more learning resources will be shared.

Prerequisites

Grading

  • A >= 95%, A- >= 90
  • B+ >= 87%, B >= 83%, B- >= 80%
  • C+ >= 77%, C >= 73%, C- >= 70%
  • D+ >= 67%, D >= 63%, D- >= 60%

Resources

Recommended (not required) textbooks / e-books

These books give you a good theoretical understanding and are very useful in research design.

  • [GRS] Grimmer, Justin, Margaret E. Roberts, and Brandon M. Stewart. 2022. Text as Data: A New Framework for Machine Learning and the Social Sciences. Princeton, New Jersey Oxford: Princeton University Press.
  • [SJ] Scott, John. 2017. Social Network Analysis. Fourth edition. Thousand Oaks, CA: SAGE Publications Ltd. (different versions are fine)

These books/sources introduce more technical and hands-on details.

  • [GS] Gentzkow, Matthew, and Jesse M. Shapiro. 2014. Code and Data for the Social Sciences: A Practitioner’s Guide. https://web.stanford.edu/~gentzkow/research/CodeAndData.pdf.
  • [JM] Jurafsky, Daniel, and James H. Martin. 2022. Speech and Language Processing. 3rd draft. https://web.stanford.edu/~jurafsky/slp3/. (the authors generously made their book publicly available, check their website and use the latest version)
  • NetworkX (the package’s documentation and the references cited are the best place to start in terms of technical details)

Presentations from previous semesters:

Acknowledgements

  • 2022: The course is partly supported by the Teaching Innovation Grants 2022-23 from the Center for Teaching and Learning.
  • 2019: The special events were supported by UT Austin Graduate School’s Academic Enrichment Fund and RGK Center Special Funds for Data Science Speaker Series at the LBJ School of Public Affairs. Co-sponsors also include Center for East Asian Studies, UT Library Research Data Services. The computing resource for the one-day data hackathon was supported by the XSEDE Educational Resources.
Core Courses
Instruction Mode
inperson