Text Mining: the role for libraries?

Text Mining: the role for libraries?

Time: 14:00 – 16:30

Date: 23/11/2017

Location: Room 417, DMS Watson Science Library

Text mining – also known as Text Data Mining, Text analytics and Distant Reading – refers to a broad range of processes for extracting information from text. This includes visualization of a single text, finding patterns in large corpora and topic modelling.

Text Mining presents exciting opportunities for researchers across all disciplines.  The expanding volume of literature, the growing interdisciplinary nature of research and the ever-decreasing cost of computing power makes text mining an increasingly powerful tool for researchers. However, despite the potential benefits, the use of text mining in research is still limited.

There are a number of reasons for this; legal barriers, difficulty accessing materials and a lack of knowledge on potential tools and techniques are some of the major ones. Is there a role for libraries to play in overcoming these barriers?

The Research Data Management team have been working with colleagues from the library and Research IT services on a session exploring the potential role libraries could play in supporting Text Mining.

The session will provide:

– an introduction to (potential) uses of text mining in research (Daniel van Strien)

– an outline of some of the legal issues surrounding text mining (Chris Holland Copyright Support Officer at UCL)

– examples of some of the research being done using text mining approaches by UCL researchers in collaboration with Software Developers from Research IT services (Tom Couch, RITs and Raquel Alegre, Research Software Development Group)

The session will allow time for discussion around the potential role of libraries in supporting text mining and present some options for further activities.

If you would like to attend please send an email to d.strien@ucl.ac.uk