Exploiting Digitised Newspapers for Research

The Europeana Cloud project is seeking researchers from anywhere in Europe who are interested in innovative ways of working and researching with historic newspapers.

Via a separate project, Europeana Newspapers, a corpus of newspapers drawn from the digitised collections of over 20 libraries in Europe has been created - see http://theeuropeanlibrary.org/tel4/newspapers/

This corpus includes over 10 million pages of OCR'd full text and images, and metadata records relating to several million more issues. Much of the data is in the public domain and available for re-use.

Within Work Package 3 of Europeana Cloud, developers and human-computer interaction experts now wish to work with digital humanities or social sciences researchers to build services and tools that exploit this data and help answer research questions that cannot practically be researched without technology.

For example:

- What is the typical sentiment in the reporting of different papers on specific historical events?
- To which locations are historical protagonists tied in the reporting and how does this evolve over time?

Within the Europeana Cloud project, similar such tools have been built before for early modern philosophers and musicologists.

If you or your research group is interested, please fill in this form in which you briefly (5-10 lines) describe your group and research interest, as well as some research questions you would like to explore with novel technologies.

Deadline: Friday 27th March

Warm regards,

Erik Duval, University of Leuven
Alastair Dunning, Europeana Foundation
Kees Waterman, Data Archiving and Networked Services (DANS)
    This is a required question
    This is a required question
    This is a required question