Tracking, exploring and analyzing recent developments in German-language online press in the face of the coronavirus crisis: cOWIDplus Analysis and cOWIDplus Viewer
Wolfer, Sascha, Koplenig, Alexander, Michaelis, Frank, Müller-Spitzer, Carolin
–arXiv.org Artificial Intelligence
The primary data source is the RSS corpus which is used both in cOWIDplus Analysis and the cOWIDplus Viewer. The former is a static HTML page that is updated on a weekly basis and seeks to analyze how the diversity of the vocabulary is developing in the light of the coronavirus crisis. The latter is an online application that enables both researchers and the broader public without data processing and analysis skills to explore the development of word forms through time. As time passes and the impact of the coronavirus crisis on language presumably becomes much weaker than in March and April, we believe that the Viewer will still prove to be a valuable tool to explore a historical record of German press language during a global crisis. Also, it enables the research community to compare the effects of such a (hopefully) singular event like this global pandemic to other events with large-scale implications (e.g., the US presidential elections later in 2020). In addition, we argued that the Viewer can also be used to analyze developments in vocabulary as close to real-time as possible. One obvious expansion of the scope would be to include more RSS sources in the corpus. This would expand the coverage of German language sources but would also allow the construction of corpora for other languages.
arXiv.org Artificial Intelligence
Mar-21-2023
- Country:
- Europe
- Germany (0.05)
- Switzerland (0.04)
- Austria (0.04)
- Europe
- Genre:
- Research Report (0.51)
- Industry:
- Technology: