Join us in Digital Text Laboratory when we develop our own text mining applications in the computerClass. This autumn we will be working in R and focusing on basic applications of natural language processing and machine learning to full-text corpora.  The class is targeted at graduate students in the humanities (MA and PhD) with an interest in text mining, but without previous experience with programming or statistics.

Contact Julie Markussen (julie_km@hotmail.com) if you or your students want to join the computerClass.

Friday October 9, 11:00-15:00

Interacting Minds Centre (for late arrivals class is in meeting room in 1461:516)

Digital Text Laboratory|DTL

With the advent of KDD (Knowledge Discovery in Databases) and the 4^th paradigm (data intensive scientific discovery) research using large quantities of unstructured text-heavy data (i.e., text mining) has come to the forefront in all domains of the natural and social sciences. If the humanities and arts are to benefit fully from this development, it is imperative that we have the necessary knowledge, tools and infrastructure to develop and evaluate text mining in accordance with our domain-specific standards. These are time and resource demanding tasks, especially in a humanities culture where most researchers conduct solitary research. To minimize cost and facilitate the application of text mining in the humanities, we have established the Digital Text Lab (DTL), a creative communal space for researchers who want to or already work with text mining in humanities and arts research domains. DTL organizes learning activities, develops humanities text mining tools, and offers a range of services related to research and teaching.

For more information contact Kristoffer L. Nielbo (kln@cas.au.dk)