Skip to main content

COVID-19 Update: Although the Gould Library building remains closed, the library staff continue our commitment to support the teaching and research needs of the Carleton community. Information on remote access to library resources and services will be updated regularly on the Remote Resources and Guidance for Library Users page and this FAQ. Please do not hesitate to contact us if you need additional assistance.

Digital Text Analysis and Text Mining

Finding word trends across large bodies of text.

Picking a tool

There are many tools that can help you analyze your text. Here are a few that we use most frequently here at Carleton.

  No
Coding
Required
No
Server
Required

Load
My Own
Documents

Analyze
Parts of
Speech
Analyze
Page
Layout
Access
Notes
Voyant x x x     Free
Tableau x x x     Instructions
HathiTrust   x   x x Carleton Login
Other
(see below)
- - - - - -

Voyant Tools

Tableau

HathiTrust Text Analysis

1) Start by finding and saving sets of documents you wish to analyze

Note that any documents labeled as coming from Google scanning will not be available through the API. Other text analysis may still be possible depending on what you want to do.

2) Analyze your HathiTrust documents using HTRC Analytics.

3) You may also need Python or Calibre, depending on which analytics you want to run and what text conversions you need to make

Other Tools and Resources