Skip to main content

You can still access the UC Berkeley Library’s services and resources during the closure. Here’s how.

Text Mining & Computational Text Analysis: Sources


Newspapers & Magazines

Available by request: ProQuest Historical Newspapers

Researchers may request OCR full text from any of the following specific newspapers for a specific time period, though requests will require significant processing time:

  • Chicago Defender (1910-1975)‎ - requested Spring 2018
  • The Baltimore Afro-American (1893-1998)

Scholarly journals

Citations & Metadata

Government Documents

Linguistic Corpora


Social Media & Internet Sources

Historical & Archival Collections

Available by Request: 

Adam Matthew Digital 
Contact History Librarian Jennifer Dorner ( to request access to OCR text and full metadata from any of Adam Matthew Digital's primary source databases.

Gale Digital Collections
Request access to Gale content for text analysis purposes, including access to OCR text from databases like the Eighteenth Century and Nineteenth Century Collections Online, as well as content from Gale’s newspaper archives. See Gale's FAQ (pdf) or brief description for more information. Email


Data Repositories

Please scrape responsibly

For help
Send questions about text and data mining access to library resources to this shared email above, which brings together librarians and campus partners with subject, copyright, technical, and licensing expertise. 

  • For help with text mining tools and software, check out the D-Lab.

What is text mining?

"Text Mining is the discovery by computer of new, previously unknown information, by automatically extracting information from different written resources... The difference between regular data mining and text mining is that in text mining the patterns are extracted from natural language text rather than from structured databases of facts."

- from What is Text Mining? by Marti Hearst (2003)