Text Analysis

Approximately three-quarters of all digital data is recorded in the form of unstructured texts. Computational Text Analysis methods allow us to systematically analyze patterns found in these texts at scale, whether we are studying tweets and social media posts, or digitized texts from centuries ago.

Researchers from fields as diverse as English, History, Computer Science, Linguistics, Psychology and Brain Sciences, Public Health, and Sociology experiment with and adapt text analysis techniques. Thus, there is an ever-growing need to connect such researchers across disciplinary boundaries.

Here at Dartmouth, the Dartmouth Library and Research Data Services are taking the lead in facilitating inter-disciplinary communication and collaboration. Under our Text Analysis Initiative, we seek to bring together scholars, teachers, staff, and students who share an interest in computational text analysis. We do so in the following ways:

• Organizing a Text Analysis Working Group or community of practice
  • including regularly scheduled events
  • an online forum for the exchange of ideas (hosted on Slack)
• Facilitating Campus-Wide Access to Text and Data Mining Platforms and Tools - see the pages below about ProQuest TDM, Constellate, and HathiTrust's Research Center.
• Offering Workshops and Training
• Research Data Service's GitLab repository of Python code and notebooks for text analysis
• Reference guides with links to external tutorials and resources

To learn more about the group and how to participate visit our webpage here (also found on the tabs to the left).