To content
Fakultät für Informatik
Project Group "HistWeb"

Project group "HistWeb" submits final report

Detail view of a single newspaper page © PG HistWeb​/​TU Dortmund

Students from the project group "HistWeb" successfully completed their work on an interactive website for analyzing and managing historical newspaper archives.

Master students from the TU Dortmund University developed a platform for analyzing historical newspapers in the "HistWeb" project group. The platform enables users to extract information from the large number of newspaper articles from the past centuries, most of which are only available as digital scans and cannot be processed by traditional search engines. This makes it easier to rediscover past events that were previously inaccessible due to the large amount of data and challenging to read Fraktur script. In addition to fully automated text extraction from the scanned documents, the web-based platform also includes features that simplify searching, such as automatic recognition of important terms, word clouds for a quick overview, and a natural language and advanced search function.