14  Application II: Examples

We continue with the individual group activities.

14.1 Virtual RStudio

• https://simplevm-proxy.bihealth.org/causalmink_100/

14.2 Possible activities

• Bring your own example: Any digital collection of texts or images can be used. I will help with reading and preparing the data and integrating them into our workflows. Your task is to figure out which kind of content analysis measures are possible.
• Tennis data: What is asked in tennis press conferences? Large set of questions scraped from ASAPsports. Smaller set of validation data with human-classified topics.
• Health searches: Identification of health-related search engine queries. Follow-up project to the one discussed in the lecture.
• Instagram posts by German politicians during the 2021 Bundestag elections. From a study by Dennis Steffan
• Use the Explainable Detection of Online Sexism (EDOS) data.