The JISC digitisation team is currently planning an international grant competition to look at the exploiting text mining methodologies for digitised content.
Provisionally called the Million Books Challenge, the competition will see how analysis of large corpora of texts, images or other digital material can open up new avenues for research.
Alastair Dunning gave an introduction to text mining and outlined plans for the competition at the JISC Collections AGM (20th November 2008)
Thanks to Ian Gregory and Andrew Hardie (University of Lancaster) for providing the case study
One reply on “Introduction to Text Mining on Digital Content”
After some more discussion, it looks like the competition will be called ‘Digging into Data’, rather than the Million Books Challenge