Python for Computational Social Science and Digital Humanities

Humans generate messy data. While statistics-focused environments like R and Stata are great for data analysis, these specialized tools can be difficult to use with data that defies tabular representation. Human data, like written language, social relationships, images, and social media content, require flexible tools that can handle complexity. In this talk, we will provide an overview of Python, highlight how this free and open-source programming language supports digital humanities and social science research, and discuss Cornell and web-based resources to help you get started using Python in your research.

Slides: www.cac.cornell.edu/education/CAC Python for Computational Social Science and Digital Humanities 2023.pdf


0:00 Introduction
2:13 What is Python
5:30 How Python enhances research
8:12 Literate analysis with computational notebooks
12:59 Python packages for research
19:12 Python in your research workflow
20:13 Data wrangling: digital traces, geolocations, and visualization
28:49 Data wrangling: text as data, statistical simulation, and visualization
40:34 Data collection: web scraping
44:11 Other applications: Network and relational data, machine learning, visualization, and agent-based models
46:10 Guides and Resources
51:00 Appendix 1: Installing Jupyterlab Desktop