Paul Vierthaler Workshop: “Visualizing Stylometric and Intertextual Relationships in Large Textual Corpora”

In this workshop, Paul will demonstrate how to perform and visualize two important techniques for exploratory document analysis. First, he will introduce how to conduct stylistic analysis using principal component analysis (useful for detecting authorship and genre-based stylistic differences). Then he will show a workflow for detecting and visualizing intertextuality between two or more works. In this workshop, we will work with a demonstration corpus of English language texts. By the end of the workshop, you will be able to visualize general stylistic similarities and both exact and fuzzy quotation using adjustable criteria, which will allow you to quickly study a corpus of documents. If you would like to participate, please install the Anaconda distribution of the Python programming language. This is free software available at https://www.anaconda.com/download/ No experience with programming is assumed, so all are welcome! The corpus and scripts we will use will be available at https://www.github.com/vierth/uvaworkshop