ProQuest TDM Studio is a text and data mining platform which brings notebook-based text and data mining tools to millions of Library-licensed newspaper articles, dissertations and primary sources. It provides both Python and R interfaces for research and teaching, alongside push-button data visualizations for geographic analysis and topic modeling.
Through ProQuest TDM Studio, users can access and analyze UC San Diego-licensed ProQuest content, which includes several major daily newspapers (e.g., The New York Times, Washington Post, Los Angeles Times, Wall Street Journal and Chicago Tribune), numerous subject databases, and more than 50,000 other individual newspapers, magazines, scholarly and trade journals, books, and conference proceedings.
UC San Diego affiliates have two avenues to access this resource:
- Workbench provides programmatic access to licensed ProQuest content through a Jupyter Notebook environment.
- Visualizations allows users to explore licensed ProQuest content through maps and charts in a point-and-click interface.
More information can be found in the ProQuest TDM Studio documentation.
To access Visualizations, users can self-register for an account using their ucsd.edu email address.
To set up a Workbench account, or for more information about ProQuest TDM Studio in general, contact Data Science Librarian Stephanie Labou.