Skip to Main Content
Becker Medical Library logotype
Library Quicklinks and Information

Text and Data Mining (TDM): Home

The Text and Data Mining (TDM) guide provides a brief overview of TDM and available data sources for TDM projects.

What is Text and Data Mining (TDM)?

Data mining free icon

Text and data mining (TDM) refers to large-scale computational analysis to extract previously unknown information from digital text files or data sets to identify, extract and analyze patterns and trends. See: What is Text Mining? Marti Hearst, 2003.


Becker Library has agreements with vendors and publishers for subscribed library resources such as journals and databases. Some agreements allow for TDM projects by authorized researchers on campus.

All subscribed library resources are governed by license agreements that may include usage rights for TDM projects. Researchers using library resources for their TDM project are advised to check vendor or publisher policies before undertaking a TDM project and to abide by the terms/stipulations of the license agreement that governs the resource. Examples of stipulations include registering and using the API from the vendor or publisher before starting a TDM project, a limit on the number of requests, use of a secure internal server for the duration of the project, to name a few. A few vendors or publishers of subscribed library resources do not allow for TDM projects under any circumstances.

A violation of a license agreement for a TDM project could result in the loss of resources for Becker Library. An example of a violation is not using the API from the vendor or publisher.

Sources for TDM

Researchers can use subscribed library resources (see Library Sources tab) such as journals and databases, or openly available data such as Open Access journals (see Free Sources tab) for their TDM project.

Contact Persons

Questions? Please contact Denise Hannibal or Cathy Sarli.