Sunday, June 5, 2016

Voyant Tools General Features

By Kenton Rambsy

Voyant has built in interfaces that automatically generate data visualizations from the content a user uploads. For literary study, visualizations can graphically illustrate a variety of numerical correlations such the ranking of words, deviations and categorical subdivisions of language trends, correlations between multiple documents.

Below are five general tools I used to analyze short fiction by Zora Neale Hurston and Richard Wright


Corpus Summary is a tool that provides a simple, textual overview of the current corpus. This includes number of words, number of unique words, longest and shortest documents, highest and lowest vocabulary density, most frequent words, notable peaks in frequency, and distinctive words.

Collocates provides an ordered list of word collocation for a specified word and document. A collocate is the habitual juxtaposition of a particular word with another word or words with a frequency greater than chance. The tool provides a sortable table of word collocation for a specified keyword in a specified document.

Contexts displays a table contextualizing a selected word with the phrases or paragraphs of text that directly precede and follow each instances of the word throughout the corpus.

Document and Terms is a table displaying all of the words in a corpus with accompanying information such as the count (number of times word appears), relative frequency (approximation of the number of times a word will appear everyone 1million words based on usage in a given document), and trend graph (illustrates the distribution of a term within linear segments of a document).

Reader provides a viewing window to allow the user to read the full text of the corpus that they have imported into Voyant Tools.

Notebook on Voyant Tools
"Seshat: A Digital Humanities Initiative" at Howard University 

No comments: