FACT wants to develop software enabling the computer to automatically enrich a corpus of Dutch folktales with metadata such as names, keywords, the genre, a summary and a catalogue number (or folktale type).
Research will focus on the question if automatic corpus analysis can offer new possibilities for the classification of folktales by means of clustering. The classification algorithms developed in the project will be integrated in user-friendly tools to support annotation and exploratory research of the folktale corpus. Using these tools, variability in oral and written transmission can be researched, as well as the pros and cons of human classification and computerized clustering.
FACT Midterm poster
Project leaders: Theo Meder, Mariët Theune
Postdoctoral researcher: Dolf Trieschnigg
PhD researcher: Dong Nguyen
Programmer: Iwe Muiser
Advisory board:
Franciska de Jong (University of Twente)
Djoerd Hiemstra (University of Twente)
Antal van den Bosch (University of Nijmegen)
FACT is supported by the CATCH (Continuous Access to Cultural Heritage) programme of the Netherlands Organisation for Scientific Research (NWO).
FACT progress wiki (login required)
