Everyone is talking about text analysis. Is it puzzling that this data source is so popular right now? Actually no. Many of our data sets in social sciences rely on (hand-)coded textual information. If you want to learn more about how you an automatically extract information from textual data and what you can then do with it, have a look at the newest blog post on MZES Methods Bites that I co-authored with Cornelius Puschmann.

Throughout the blog post, we rely on two different datasets (the UN General Debate data by Mikhaylov, Baturo, and Dasandi and pre-labeled news data by Kohei Watanabe) and guide you through the basic steps to read in and preprocess the data and then showcase how to analyze the data with supervised and unsupervised machine learning techniques.