WhoIsInTheNews is a web application which collects every day RSS feeds from various German news sites. The plain text from these feeds are send through some tools from the OpenNLP suite: tokenizer, sentence detector an named entity recognizer. The named entity recognizer was trained with the Named Entity Model for German, Politics.
Finally, the named entities are extracted and stored in a database.
WhoIsInTheNews offers functions and visualzations to analyze the collected named entities. Click through the menu on the left to explore the WhoIsInTheNews and the stored named entities.