Text-based or written information in natural language constitutes a major part of the research objects within the humanities and arts. That such information is becoming widely available in digital formats, either because it is created in a digital environment (e.g., Wikipedia or Facebook) or because it is digitized (e.g., Google books, Project Gutenberg, or Grundtvig.dk), opens many new and relevant research opportunities. Humanists can nevertheless experience a lack of digital competences, when faced with methods and tools for text mining and analytics (i.e., the discovery of useful and non-obvious patterns in large collections of text-based information). This is unfortunate, firstly because many humanists cannot access methods and tools offered by the digital revolution (often identified with digital humanities) and, secondly, because mining of valuable texts is left to researchers that are far less competent in understanding the texts’ meaning and context.

This workshop presents basic text mining tools and methods in the humanities at an introductory level. It will supply participants with the sufficient knowledge and experience to initiate a text-mining project of their own. The core of the course is three hands-on modules, through which participants will become familiar with software and a range of methods for analyzing text meaning. The workshops will be supplied by presentations and discussions of research design, best practice, and reporting standards. The participant is not expected to have any experience with text mining (i.e., programming, statistics or visualization), but should have an interest in applying digital tools and methods on their own research.

For registration, please contact Kristoffer Laigaard Nielbo (kln@cau.au.dk)