Voyant: Online Text Analysis Tool

Caitlin Dempsey


Voyant (http://voyant-tools.org) is an online text analysis tool that allows users to enter one or more URLs, a block of text, or a set of text documents, and see the results of terminology used.  Voyant is an open source tool that lets users understand which words are most frequently used in a body of work and the interrelationships between those words.  I used a test page from the bark entry in Wikipedia to try out the tool.  After entering the URL, the tool returned, within a couple of seconds, a detailed visual and quantitative analysis of the word content.  

Voyant text analysis of the Bark entry on Wikipedia.
Voyant text analysis of the Bark entry on Wikipedia.

The site contains a very well developed set of explanatory pages that not only explained how each component of the tool worked, but also provided examples of that function in use.  I found that this helped to better my understanding of how each aspect of the tool could be used to analyze text.  

While the tool was very quick at analyzing the Wikipedia page I entered, the tool didn’t appear to work for all sites.  For example, I tried to have it analyze an article from GIS Lounge and the tool, even after waiting fifteen minutes, was still showing a processing indicator.  Similarly, the tool had the same response when I tried to analyze a New York Times article.   No error message was provided by the tool for either of these tries.  

            Overall, I can see that this text analysis tool would be valuable researchers in the digital humanities and geographic research who want to analyze the context and temporal usage of a word.  For example, the tool could be used to analyze a corpus of works over a given time frame to understand the trends in usage of specific words or phrases. Even within the context of a single page of text, when I clicked on a word, the graph on the upper right side showed me the frequency of the word over the course of the page.  This let me know whether the word was used most frequently at the beginning, middle, or end of the text.  


Photo of author
About the author
Caitlin Dempsey
Caitlin Dempsey is the editor of Geography Realm and holds a master's degree in Geography from UCLA as well as a Master of Library and Information Science (MLIS) from SJSU.

Free weekly newsletter

Fill out your e-mail address to receive our newsletter!