Text & Data Mining

ProQuest TDM Studio provides computational access to the subscription content (primarily newspapers) that the Library subscribes to via ProQuest. This resource is an analytical tool to support text and data mining and similar methodologies. You will be able to download derived data and visualizations, but not full-text of articles.

Introduction to ProQuest TDM Studio video (about 4 mins)

There are two main paths for interacting with TDM Studio.

1) The visualization dashboard  is a basic visualization platform for discovering patterns in a result set based on geography or using tools such as sentiment analysis. You don't need any coding experience 

Screenshot of the geographic visualization tool 

2) The workbench dashboard provides a private collaborative workspace for individuals or small teams to collect datasets of search results, and perform analysis on them in a hosted Jupyter Notebook environment, using either Python or R scripting. You will need to have some familiarity with writing code, though ProQuest provides several Notebooks with helpful example scripts to get started and perform basic TDM tasks.

Screenshot of the workbench dashboard

• You can access the TDM Studio visualization platform directly with your Claremont credentials. From the main TDM Studio page select the "Create Account" button if this is your first time using TDM Studio.
  
   
• There you will be prompted for your name and email. Be sure and use your Claremont email address. 
  

To access the workbench platform, the library will need to set up your email (and those of any collaborators) with the ProQuest support team. If you are interested in setting up a workbench, email us at digitalscholarship@claremont.edu.