Newspapers collect information about cultural, political and social events in a more detailed way than any other public record. Since their beginnings in the 17th century, they have recorded billions of events, stories and personal names in almost every language and every country daily. The importance of historical newspapers as cultural heritage is well understood. However, the recent progress of dedicated projects such as the H2020 NewsEye project (https://www.newseye.eu/) offer new ways to read and access an in-depth analysis of extensive collections of European historical newspapers. This course is intended to bring such material and tools as a rich and diverse application framework for learning or teaching Digital Humanities (DH).
This course provides an introduction to digitised historical newspaper analysis. Newspapers collect information about cultural, political and social events in a more detailed way than any other public record. They are a valuable source of information, but their analysis can be tricky, depending on the research question or the corpus’s quality. The course presents methods from natural language processing for discovering, exploiting and visualising newspapers. It discusses these methods in detail to highlight their advantages and limitations. Examples of the use of the NewsEye platform and examples of code in Python language are proposed to allow you to put into practice these exploitation techniques.
After completing this course, learners will be able to:
- Recognise methods of Natural Language Processing in analysis of newspapers
- Understand the challenges to using newspaper corpora for digital research purposes
Check out "Digital Historical Research on European Historical Newspaper with NewsEye Platform"Go to this resource