This hands-on workshop will introduce foundational concepts in natural language processing (NLP) as well as techniques for analyzing text (natural language) data using Python's Natural Language ToolKit (NLTK) library. We will work through an entire basic NLP workflow covering acquiring text corpora from the web, text pre-processing, summary statistics and visualization, and building generative models.

This workshop will be delivered by the HBS Research Computing Services group in partnership with the Data Science Services group at IQSS.

Visit the Harvard Training Portal for details and registration information (requires HarvardKey).