Data and NLP project

Mining German Public Discourse

Using data mining, language models, and visualization to examine German news coverage and parliamentary speech.

Status Ongoing

Tagesschau code Bundestag code

This project applies computational methods to several sources of German public and political discourse. It is an umbrella for related experiments rather than a single dataset or model.

News coverage §

The Tagesschau work collects articles from tagesschau.de and examines patterns in their timing, length, language, and subject matter. It also includes an experiment in fine-tuning a German language model to generate articles in the style of the collected news coverage.

Parliamentary speech §

The Bundestag work collects and parses historical parliamentary transcripts to study word associations and how political language changes over time.

Connected work

Outputs

2 entries

Articles and documentation

Mining the Bundestag (22 Jan. 2023)
Did you know that the German parliament publishes protocols for all of its proceedings in PDF format? It is relatively straightforward to download and parse them, so we can easily collect a dataset of transcripts of what seems to be every speech in the Bundestag since the Second …
Code
Categories: Data Mining
Tagged with: Bundestag · Data Mining · Generative Models
Thumbnail for Mining the Bundestag
Mining tagesschau.de (26 Nov. 2022)
I like to read tagesschau.de, so I wrote a script to scrape it in regular intervals. My original goal was to determine which articles stay on the front page the longest, which ones allow commenting (a feature that seems to have been disabled almost entirely since March 2020), and …
Code
Categories: Data Mining
Tagged with: Tagesschau · Generative Models · Data Mining
Thumbnail for Mining tagesschau.de

← All projects