The Claremont Colleges Library offers institutional access to the Constellate text and data mining platform. It is an open-source educational project from ITHAKA/JSTOR, a nonprofit organization that aims to improve access to education and knowledge, that integrates access to scholarly content and open educational resources into a cloud-based lab to help students learn and faculty teach text analysis and data skills.
Constellate hosts a series of thorough, robust tutorials that show how to use Python to analyze textual data, and is gradually supporting similar approaches using R. It provides instruction on how to use natural language processing tools such as spaCy and NLTK, and Large Language Models (LLMs), as well as basic and intermediate Python instruction to help learners get up to speed. These tools can be applied to the rights-cleared full-text content from JSTOR and other providers in a hosted JupyterLab environment.
How to Access
The Claremont Colleges Library has a full membership to the platform (as of July 1, 2024).
Individual users will need to follow the link on this page to access the Constellate page which will prompt you to sign in with your institution username and password. However, you will then need to create a free account with their email address.
Using Constellate
For more information on how to use Constellate (and text analysis more generally) and to see example projects and use cases, you can visit:
Should you have any additional Constellate-related questions, please contact digitalscholarship@claremont.edu.