ProQuest TDM Studio
To access TDM Studio, please create a personal account using your rutgers.edu email address. If you have a ProQuest account with the same email address, during the account creation process, TDM Studio will offer the option to use your existing ProQuest account.
ProQuest TDM Studio is a text and data mining tool that you may use to analyze content from nearly all of Rutgers University Libraries' ProQuest databases. These databases include a wide variety of resource types, including indexing and full text for newspapers, scholarly and popular journals, dissertations and theses, primary sources, government documents, and more. TDM Studio allows you to perform large-scale analyses that are not possible within the ProQuest databases interface. It offers two main analysis options:
- Visualization: A beginner-friendly way to do Geographic Analysis, Topic Modeling, or Sentiment Analysis on a dataset of up to 10,000 records using a simple interface without coding.
- Workbench: A way to perform large-scale data analyses by creating a dataset of up to 2 million documents and:
- Export metadata (not full text) to a .CSV file to analyze outside of TDM Studio
- Analyze indexing and/or full text by coding in Python & R in Jupyter Notebook within TDM Studio.
Within ProQuest TDM Studio, on the dataset creation screen, you may select from all of Rutgers' ProQuest databases whose contents may be analyzed via TDM Studio. You may add filters such as date, publication title, and source type to narrow your dataset. Note that saving a large dataset may take multiple hours, so completing your analysis might require multiple sessions.
Varies per collection; documents date from ancient times - 21st century.