O'Malley Library: DAsH: Text Analysis

What is it?

Text analysis is performed when a text or a large group of texts is tabulated and analyzed, to look for trends in word frequency, context, concordance, topic or other measurements. By this method, large chunks of information can be summarized and the knowledge of the scholar can be applied to interpret the results.

Getting Texts

HathiTrust Digital Library
HathiTrust is a partnership of academic & research institutions, offering a collection of millions of titles digitized from libraries around the world.
Project Gutenberg Online Catalog
Project Gutenberg offers over 54,000 free eBooks: You will find the world's great literature here, especially older works for which copyright has expired.
Internet Archive: Texts
The Internet Archive offers over 12,000,000 freely downloadable books and texts.
BeautifulSoup
If you have some Python and HTML skills, this script library will be extremely helpful to you if you are looking to scrape information from webpages.

Software and Programs

AntConc
A program that takes text files and lets you search for keywords in context, n-grams, and concordance within one file or across a group of them
Bookworm: HathiTrust Digital Library
Search for trends in word frequency in the texts of the HathiTrust Digital Library. Can customize to only look at certain genres or for certain years.
Bookworm: Movies
A visualization that allows you to look for trends in word use in dialogue from thousands of TV shows and movies.
HathiTrust Research Center
Apply word-frequency, topic modeling and other text-analysis tools to specific texts within the HathiTrust Digital Library
IBM Natural Language Understanding Demo
A demo of IBM's Natural Language analysis tools that finds entities, keywords and does sentiment analysis. To be noted, however, it has a 50,000 character limit so can only be used for shorter chunks of text.
MALLET: MAchine Learning for LanguagE Toolkit
A topic-modeling program designed by MIT. See the Programming Historian site for a tutorial in its use.
Textalyser
An extremely basic text-analysis tool on the web that provides tables for frequently used words or phrases, and analyses the frequency of word length and syllable count.
Voyant
A web-based tool that will take text documents, pasted in text, or links to websites and analyze them for trends, frequency, words in context. It also provides wordclouds and other visualization options.
Word Seer
This program analyzes your texts for how parts of language are used, word counts and n-grams. You will need Python skills and access to the text you want to analyze as XML in order to use this.
Word Tree
A web-based program that will take pasted-in text and display the context that a given word is used in. You can see whether it is often followed or preceded by a given word.
Word Wanderer
This web-based program takes your pasted-in text and analyzes if for frequently used words, words used in context with each other, and lets you sort by parts of language (nouns, adjectives, verbs, pronouns, etc)