Voyant Screenshot

Text Mining and Analysis

Text mining, also referred to as text analysis, is the process of examining texts to discover new information or answer specific research questions, using algorithms that can quickly identify facts, patterns, and relationships in large collections of documents (e.g., emails, social media posts, blog posts, books, articles, diary entries, etc.). This information can be converted into structured forms for visualization using charts, graphs, mind maps, word clouds, and more.

Text mining differs from manual text analysis in that analytical processes are automated and applied to collections of texts that are usually too large to be read and analyzed by humans. The algorithms, math, and statistics used in text mining also enable more quantitative analysis and the uncovering of information that is easily missed by human scrutiny. However, text mining is most useful when combined with manual analysis and critical interpretation of the results of text mining.

Areas of Support

We provide support for text mining and analysis in the following areas:

  • Getting Data: finding and acquiring text data
  • Preparing Data: extracting, cleaning, pre-processing, and structuring text data for mining
  • Methods & Tools: identifying appropriate methods and tools for research questions/goals
  • Project Management: developing and managing text mining research projects
  • OCR Workstation: An OCR workstation with ABBYY FineReader 14 is located just outside of the Digital Stewardship Lab. This workstation also includes a microfilm reader and scanner. This workstation is available to any member of the University of Pittsburgh community at any time Hillman Library is open, and can be reserved online.

Services

We offer the following services for text mining/analysis and OCR:

  • Consultations: make an automated appointment, or contact us to set up a meeting.
  • Workshops:
    • We offer several workshops every Fall and Spring semester, open to the Pitt community and general public, free of charge. See what we have to offer here.
    • We also offer workshops by request for classes and groups (time and expertise permitting). Contact us to make an inquiry.

Upcoming Events