*** This version of Confluence is for testing only and contains a copy of content from June 29th 2026. No changes will be preserved. ***
An overview of computational analysis of text, foundations, and exploration of challenges and strategies.
| Table of Contents |
|---|
...
Preparation
- Bring text to play with explore in Voyant. Input format Format can be plain text, a PDF (with OCR), a MS Word Document or a URL (for HTML analysis of web pages). Upload of material will be subject to the Voyant privacy policy, so bring text you can safely share.
- Bring a laptop to support your explorations.
- Look through this lesson plan, develop your questions - and bring them to class.
- Optionally - the intrepid may want to obtain a login to the HTRC Portal, create a workset and run a few algorithms in advance of this lecture. Documentation for obtaining a sign-on and documentation for the portal will be helpful.
Going down the rabbit hole: anatomy of a digital book
How is a digital book made? How does the structure relate to its function? What opportunities does this afford us in terms of text analysis?
(1) Consider this book: Alice's Adventures in Wonderland. Explore the controls on the right side of the page turner.
...
(2) Now explore the controls at he the top of the page turner.
- There is a box labeled "search in this text". What can you deduce about the book from given this functionality?
- What do the other controls do? Is there a way to summarize this class of controls? What underlying logic might you predict that coordinates these functions? (Food for thought...download and display in a browser.)
(3) What might this page be? (It also has this view.) Is this also part of the book? When and how might it be used?
(4) Diving deeper into text. Optical Character Recognition (OCR) processes are not perfect. Consider some areas of special challenge:
...
Computational analysis of text
We count tokens - What is tokenization? Why tokenize? What are some strategies used to tokenize?
(1) Let's look again at the Arapaho gospel of St. Luke. Switch to text view.
- Is this OCR accurate to the visually captured page?
- What is a word? How would you define this for "word" to a computer?
- What isn't a word? How would you tell a computer to exclude these?
- Consider languages with which you are familiar. Can you think of special cases where tokens might contain more than one word?
- What sets of rules would we need in order to tokenize effectively? Would these be ordered in any specific way?
- Is there a "right way" to tokenize?
(2) Discussion: What are the opportunity points that the structure and arrangement of a book afford?
- How do challenges with OCR intersect with strategies for computational analysis of text? What might be effective strategies to deal with these challenges?
- What exactly is the "text"? Can you think of parts of a book that you might not want to include in your analysis? Why or why not? If you would, how would you exclude these parts?
Introducing Control -
...
Microanalysis
...
with Voyant
Voyant is a low barrier text analysis tool that delivers a rich, interactive interface and a variety of visualizations based on token counts within a single or a few texts. Input format can be plain text, a PDF (with OCR), a an MS Word Document or a URL for HTML analysis. Upload of any material will be subject to the Voyant privacy policy. Sample texts and URLs for analysis are listed below for experimentation, but feel free to use other source data that interests you.
- Sample texts, courtesy of Project Gutenberg. Use the plain text version.
- Crane, Stephen, 1871-1900. The Red Badge of Courage: An Episode of the American Civil War.
- Dickens, Charles, 1812-1870. A Tale of Two Cities.
- Upham, Charles Wentworth, 1802-1875. Salem Witchcraft, Volumes I and II
- Sample URLS: copy and paste into the Voyant upload browser window to get started.Sample URLS: copy and paste into the Voyant upload browser window to get started.
Economics of Crisis - http://www.economicsofcrisis.com/indications.html
Instructions to major John Sullivan. Washington, George, 1732-1799. The writings of George Washington from the original manuscript sources. Electronic Text Center, University of Virginia Library. Internet Archive.
- Copyright Law of the United States of America and Related Laws Contained in Title 17 of the United States Code - http://www.copyright.gov/title17/92preface.html
- Sample visualization: Dr. Martin Luther King, Jr. I Have a Dream speech.
We calculate frequency
- We can express our counts simply (as counts), or we can express them as frequencies. Why calculate frequencies?Is either representation misleading? If so, in what ways?
(1) Visualization of derived data
- Explore visualizations in the "dashboard" that results from analysis of uploaded text. Change Explore changing the options in the dashboardfor visualizations.
- Discuss the relative merits of the various visualizations.
(2) Exerting control
- Experiment with stopwords
- Experiment with the slider for word counts counts
- Consider raw vs relative frequencies
(3) General questions) Discussion
We calculate frequency
- We can express our counts simply (as counts), or we can express them as frequencies. Why calculate frequencies?
- Is either representation misleading? If so, in what ways?
- What does exerting control do to our results? Does it change the validity of our assertions?
- How should method be explained when making assertions from results?
- Who determines what is "signal" and what is "noise"What is signal? What is noise?
Moving from Microanalysis to Macroanalysis
...
(Google nGrams
...
and HTRC bookworm)
nGrams are words or phrases, tokenized and counted in a defined corpus and displayed as a graph showing relative frequencies of those phrases as occurring over publication date. The two tools referenced below provide a basis for exploration of ngrams. Each tool is bound to secondary data derived from analysis of a different corpus, so results of the same nGram will not necessarily align.
Google's nGram Viewer. Use the links below as starting points; dynamic modifications can be made at any point. Rules for syntax can be found on the About page.
- graffiti - let's start with this, and make it more meaningful
- "Ralph Ellison" and "Invisible Man
- "lyric/lyrics"
- "Jarndyce and Jarndyce" and "Bleak House"
- vacant lot,urban renewal,gentrification
HathiTrust Research Center (HTRC) Bookworm. Again, consider these links as starting points. Rules for faceting ad controls are available on the HTRC wiki.
- monster in fiction/non-fiction/unknown
- mystery (contrast fiction and nonfiction)
- various words for "creole"
- "phonograph" in three languages
Discussion
- How easily can these examples above be refined and improved?
- Compare the two interfaces, especially as to the affordances and the limits of each.
- What additional elements of control would be useful that aren't available?
- When we see unexpected wave forms, what do we make of these?
- Do these constitute discoveries or represent errors? How can we distinguish?
- Would the flaws be due to the data, the metadata, the algorithms?
More Macroanalysis: HTRC
HathiTrust Research Center (HTRC) is a collaborative research center (jointly managed by Indiana University and the University of Illinois) dedicated to developing cutting-edge software tools and cyberinfrastructure that enable advanced computational access to large amounts of digital text. A basic orientation of HTRC services is available, and features and steps for each are documented on the HTRC community wiki. We will be spending time in the HTRC Portal looking at the results of a few algorithms as a sampling of possibilities (links below will not render for all, but are parked to make sharing easier). Algorithms in the portal can
- Compare one collection of books to a second collection, and report the differences in frequency of tokens - ShksprDunning
- Extract entities from a set of books, and list out referents of where they occur
- Person, location - WSPlaysEntityExtract
- Dates - WSComediesExtractDates (Note the wide variety of what is considered a "date")
- Dates visualized over timeline - WSComediesDateExtractSimileRemix
- Model "topics", or clusters of tokens that are statistically more likely to be found together - WSComediesTopics; WSTragediesTopics
Discussion
In general, do the results look valid? Do any of these algorithms yield results that might be considered confusing or less than perfect?
- Note that results can be downloaded. What might be advantages of this portability?
- Are there things that the researcher would want or need to know about these algorithms when making claims about results?
Image analysis
Ukiyo-e.org is a database and image similarity analysis engine, created by John Resig to aide researchers in the study of Japanese woodblock prints. The data is over 213,000 digital copies of prints from 24 institutions, and their cataloging metadata. Metadata is indexed and searchable. (Details are noted in the about page.) Resig'sImage search uses the TinEye matching engine to determine edges in an uploaded sample and compares with analyzed edges in database, returning probable matches (edge analysis).
| Gallery | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
|
More macroanalysis
- HTRC
- entity extraction
- What are entities?
- False positives/false negatives (omissions)
- Clustering - topic modeling
- define and defer for Mimno
Image analysis
...
Resources
"Formatting Science Reports." Academic and Professional Writing: Scientific Reports. University of Wisconsin - Madison, 24 Aug. 2014. Web. 03 June 2016.
...