ProQuest TDM Studio
Find source materials for TDM research
One of the most thorny aspects of embarking on a text data mining project is collecting the materials for your corpus. If you are interested in text mining newspapers, scholarly journals, dissertations, or primary sources, ProQuests’s TDM Studio may help you address this challenge.
TDM Studio provides a virtual environment in which you can run text data mining analyses on large datasets curated from library-subscribed ProQuest content. TDM Studio is a new research tool offered by the Library.
Content available in TDM Studio includes selected current and historical newspapers, dissertations and theses, scholarly articles, and primary source material that the Library has subscribed to through ProQuest. Some coding experience (e.g., Python) and familiarity with Jupyter notebooks would be necessary to run your analyses. You must first request an account before being given access to the environment.
Quick Links
- Request a TDM Studio account
- ProQuest documentation
- Library’s TDM support team: tdm-access@berkeley.edu
- Other library sources for TDM research