Special Interest Group Text Mining
The amounts of text (scholarly, historical, social) are vast, are increasing rapidly. There are more texts than one person can ever read, and keeping up with new texts is also impossible. Most collections of textual data are too large for human processing. Instead, researchers use data mining techniques to extract insights and information from such text collections (corpora).
Text mining is a research method in which large collections of written language are analyzed by means of computational and statistical techniques. This method is already employed in various disciplines at UU and UMCU, such as linguistics (extracting user-specified grammatical constructions, sentiment analysis), biomedical research (classifying research papers as either relevant or irrelevant), history (tracking concepts over time), literary studies (stylometrics, authorship), etc. The SIG aims to promote text mining as a useful research method in the UU and UMCU community, and to explore novel applications of text mining in research.
The SIG is open to all researchers at UU or UMCU who are interested in text mining. If you would like to be updated about the activities of this SIG, please register for our newsletter.
For further inquiries, please contact Jan de Boer.