Skip to Main Content

Text mining

Corpora, databases, tools, methods and further reading.

What is text mining?

Text mining is the automated analysis of large collections of text, to find hidden patterns, trends, and relationships.  

Text mining is usually applied to large sets of unstructured texts, such as news articles, books and literature, social media posts, academic publications, and language corpora.  

Text mining methods are used for different purposes, such as determining emotional tone (sentiment analysis), assigning topics (topic modeling), performing linguistic analysis, extracting information, and finding keywords for literature searches.

Why text mining?

  • Research large text corpora:  

Text mining allows you to do research on larger collections of texts, which would be impossible for a human to read and analyze. Thus, there is no need to cherry pick a selection of documents, allowing you to do research on a more comprehensive corpus.

  • Discover hidden patterns:  

Text mining methods can help you discover patterns, relationships and trends that are hard to discern by simply looking at the text. In that way, text mining can complement more traditional ‘close reading’ methods in the analysis of texts. 

  • Develop a search strategy for a literature review:

Text mining can be applied to find the right keywords to use in your (systematic) literature review. A word frequency analysis gives insight into the most frequently occuring words and themes within the analyzed corpus.  

Support

Information specialists from various faculties provide support with text mining analyses.

  • Workshops 
    We organize workshops on text mining, ranging from shorter demonstrations of text mining tools to 6-hour Python workshops. For more information and registration: LibCal. 
  • Individual support / questions
    Do you have any questions about text mining, or would you like more information on the possibilities of using text mining in your research? We can give you advice on how to find suitable corpora and databases, how to create your own corpora, or provide help with finding the right tool for your text mining analysis. Please let us know via textminingsupport@ru.nl. We are happy to help!

Workshop Calendar