Textual data are central to the social sciences. However, they often require several pre-processing steps before they can be utilized for statistical analyses. This workshop introduces a range of Python tools to clean, organize, and analyze textual data. It is intended for researchers who are new to working with textual data, but are familiar with Python or have completed the Introduction to Python workshop. 

Python is best learned hands-on. We therefore strongly encourage that users install Python 3 (https://www.python.org/downloads/) and the packages listed below. Helge will be on Zoom at 1pm to help participants with installation issues. Of course, anyone is welcome to join and watch without coding themselves.

Python packages: nltk, fuzzywuzzy, re, glob, sklearn, pandas, numpy, matplotlib

Helge-Johannes Marahrens is a doctoral student in the department of Sociology at Indiana University. He recently earned an MS in Applied Statistics and is currently working toward a PhD in Sociology. His research interests include cultural consumption, stratification, and computational social science with a particular focus on Natural Language Processing (NLP).

Access the accompanying presentation materials on IUScholarWorks