juul_document_analysis

Text Analysis Resources for JUUL Industry Documents

Created by University Libraries at the University of North Carolina at Chapel Hill in collaboration with Industry Documents Library at University of California San Francisco. To access the Jupyter Notebooks we use for our tutorials, visit our GitHub repository.

For more information about the JUUL Labs Document Collection for North Carolina, see our libguide.

We have also created a Zotero library with resources for text analysis methodology on similar collections that may serve as background reading for your text analysis project.

Introductory Tutorials

• How to use the Industry Documents Library API Python Wrapper
• How to create a type-specific dataset

Working with Specific Document Types

• Working with Emails
• Working with Spreadsheets
• Working with Documents
• Working with Audio
• Working with Audio-visual material
• Working with Slack messages

Advanced Tutorials

• Conducting a Time Series Analysis on Emails
• Conducting Employee Network Analysis
• Conducting Key word Extract and Named Entity Recognition(NER) on Emails
• Creating a RAG Model with Email Documents

MORE TUTORIALS COMING SOON

For questions about these tutorials or about conducting your own text analysis research using the JUUL Labs Documents Collection for North Carolina, please contact Rolando Rodriguez