Skip to Main Content

Text Analysis

Dartmouth College Library's guide to text analysis tools and platforms

Getting Started with Constellate


What is Constellate?

Constellate, the new text and data analytics service from JSTOR and Portico, is a platform for learning and performing text analysis, building datasets, and sharing analytics course materials.

What collections are included in Constellate?

Constellate works with various data providers including JSTOR, Portico, Chronicling America, Doc South, South Asian Open Archives, and Reveal Digital. Selected, rights-cleared content is available, and more collections are being added.  Check the Constellate website for more information.

How do I learn to use Constellate?

Constellate provides open lessons on topics such as using Jupyter computations notebooks, python basics, and various text analysis methods including Named Entity Recognition, Sentiment Analysis, TF/IDF, Topic Modeling, and Word Frequencies. Constellate's new notebook environment is a customized version of the Jupyter Notebook software designed to meet the needs of Constellate users. Each user is provided with a workspace preloaded with Constellate's tutorial notebooks and Python libraries needed to get started with text analysis on the Constellate platform.  Users can work through template notebooks using custom or pre-built datasets.