Digital Humanities and Literary Studies: Text Analysis with Python

This workshop will explore digital humanities methods for literary analysis, using the Python programming language. Topics will include: how to identify and visualize key words using term frequency and inverse document frequency (TF-IDF); how to identify clusters of topic words using latent Dirichlet analysis (LDA); how to analyze sentiment and emotion; extracting information on named individuals and places using named entity recognition (NER); collocation with keyword in context analysis (KWIC); literary data visualizations including word clouds, keyword density graphs (KDE), and word cluster network graphs; and approaches to comparing styles across works and authors.