ProQuest Studio: a new tool for text and data mining

ProQuest Visualization screenshot

The Library is pleased to announce access to the ProQuest Text and Data Mining Studio. The Studio enables researchers to mine and analyse ProQuest content, including current and historic national and international newspapers such as:

  • The Sydney Morning Herald
  • The Australian
  • The Australian Financial Review
  • The New York Times
  • The Guardian

The Studio has two interfaces: the Studio Workbench (access available on request) and Studio Visualizations (create an account online).

Through the Studio Workbench you can use R or Python to analyse up to two million documents, including newspapers, magazines, journals and books, via Jupyter Notebooks within the workbench. The Studio workbench is best suited to researchers wanting to conduct large scale analysis of texts. View current content available in ProQuest Studio Workbench and request access to the Studio Workbench by contacting with the project details and email addresses of those who require access.

Using Studio Visualizations, you can analyse up to 10,000 documents from a subset of ProQuest’s content using pre-built text mining tools. Studio Visualizations is an evolving interface which currently provides access to a Geographic Analysis model. Further text analysis methods, including topic modelling, as well as access to more content, will be released throughout the year.

Using Studio Visualizations doesn’t require coding experience and is best suited to researchers and students new to text mining, or teaching staff wanting to introduce text mining to their students.

To start using Studio Visualisations, create an account online. If you’re new to text and data mining, use the Library’s Text and Data Mining guide to get started.

ProQuest Text and Data Mining Studio is a welcome addition to the Library’s text and data mining resources. For more information, refer to the Library website for:

The Sydney Informatics Hub also offers training on coding throughout the year.

Screenshot of a ProQuest Visualization showing publications by country