The UC Berkeley Library is pleased to announce access to a new text and data mining platform, Nexis Data Lab from LexisNexis. The cloud-based platform enables users to run computational analysis in a Jupyter notebook on content licensed for use at UC Berkeley. Please take a look at this brief, two minute video to see how the environment works. Researchers should be familiar with Python or R. Each account may have up to 6 projects (workspaces), with a limit of 100,000 documents per project. The number of seats are limited, so we ask that you have a TDM project in progress.
Please view the list of content and titles available to UC Berkeley users. LexisNexis will continue to make additional content available as the platform grows. (Note that the following publications are NOT available: The New York Times (NDL does include NYT International), The New York Times Blogs, Wall Street Journal Abstracts, Information Base Abstracts, and Jane’s Defence Weekly.)
If you would like to get started using the platform, request a seat by filling out this form. The Library is holding a training session for the platform (hosted by LexisNexis) on August 15, 2022 at 9:00 AM. Please register here for the event. For more information on text and data mining platforms and resources available at UC Berkeley, please check out our guide to Text Mining and Computational Text Analysis. Contact the Library Data Services Program at librarydataservices@berkeley.edu with questions.
