Today I’ll be talking very briefly about text and data mining. My post will be short because this is not a technique I’ve used myself and I have no experience of it, although some of the researchers I’ve supported it have made use of data mining themselves. I think it has the potential to be a very useful research tool, but its limitations, covered in the presentation/transcript for today’s portion of the Research Things programme, may represent a significant hindrance. If text and data mining techniques cannot be used in the majority of key databases (those used by a majority of researchers in various fields), this is a severe drawback. Until this copyright issue is resolved, text and data mining should be used with care. As suggested in the presentation, it’s probably worth getting in touch with the team at ContentMine to check that you are applying text and data mining techniques correctly and complying with copyright.
Tags23 research things cambridge academic publishing academic writing tools altmetrics apps in libraries bibliometrics blog housekeeping camtasia critical appraisal diversity in libraries eahil eahil 2017 haslibcamp induction week international librarians network jargon and terminology language libraries library assistant library camp east library inviligator library studies literature searching mmit 2015 nhs libraries outreach private libraries publication tools public health research ambassador project royal marsden manual science libraries scopus semantics social media and libraries systematic reviews sythesising and summarising teaching and learning forum teaching theory and practice text and data mining the librarian errant the london library twitter university of cambridge libraries web of science writing for publication
Follow me on TwitterMy Tweets