Dive Into Text & Data Mining with Constellate

W&M Libraries is trialing a new database, Constellate by JSTOR (ITHAKA) through June 30th, and we want your feedback!

What is text and data mining?

Text and data mining (TDM) uses computational methods to extract and analyze large quantities of text files or data sets to quickly identify patterns and relationships. Text analytics methods include information retrieval, named entity recognition, part of speech tagging, sentiment analysis, network analysis and topic modelling.

What is Constellate?  

⁠Constellate is a text analysis platform that integrates access to scholarly content and open educational resources into a cloud-based lab. Users can apply text analysis methods to datasets and hone their skills with support from on-demand tutorials. The platform draws on content from the JSTOR corpus as well as from 100+ publishers preserving content with Portico providing millions of primary and secondary sources across many fields of study. NOTE: In order to access the full range of features, users must create or sign in with their JSTOR account.   

How can I try out Constellate and learn more?

During the trial period, Constellate will be available just like any other database using the “Database” button on the homepage. It can be found using either the alphabetical list or “Trial Databases” link.

To support this trial, we will be having a workshop with the database on Wednesday May 15th at 2:00 pm. You can register for this workshop now, and we'll post more details on the library calendar soon!

An initial training was offered on April 15th and the recording is available for those interested in learning more about the database before May 15th.

Constellate offers several events, including classes and webinars, to support users which are accessible during the trial period. They also have an extensive help page that includes 13 how-to guides to assist users with using Constellate.

Finally, we would be grateful for your feedback during the trial period. Databases are expensive and we appreciate the feedback of the W&M community along with many other factors before the purchase of any new database. For more information about this process view our new collection development policy.