Preliminary Class Business
- Enrollment
- Getting started on your portfolios. (Preview of portfolios due April 30th)
- "Thought" Essay # 1. (Due April 30th)
- Readings for next class.
- Practicum 5: Topic Modeling Instructions for this practicum | Folder of exercises on Student Work page
1. Thinking Ahead to the Class Project
2. Text Analysis (continued)
- Your Practicums:
- Some explanatory resources:
- Cosine similarity
- Practical guide to correspondence analysis (including Principal Component Analysis)
3. Concepts (and History) of Text Analysis
Readings for Class 4:
- Franco Moretti, Graphs, Maps, Trees (Verso, 2005), pp. 1-33, 91-92
- Ryan Heuser and and Long Le-Khac, "A Quantitative Literary History of 2,958 Nineteenth-Century British Novels: The Semantic Cohort Method" [PDF] (Stanford Literary Lab Pamphlet #4) (2012)
Readings for Class 5:
- Ted Underwood, "Where to Start with Text Mining?" (2012)
- Franco Moretti, "'Operationalizing': Or, The Function of Measurement in Modern Literary Theory" [PDF] (Stanford Literary Lab Pamphlet #6, 2013)
Readings for Class 6:
- The Idea of a "Concordance"
- Wikipedia article on "Concordance"
- Religious literature concordances:
- Wikipedia article on Strong's Concordance
- Strong's Corcordance Online (try it out)
- Father Roberto Busa's Index Thomisticus for the works of St. Thoma Aquinas, in Latin (try it out)
- Literature concordances:
- Shakespeare concordance (try it out)
- Beyond the Concordance: Corpus Linguistics and Digital Text Analysis
- Try out the following corpus linguistics resources and tools (read beginning of Wikipedia article on Corpus Linguistics for definition of the term):
- corpus.byu.edu
- Antconc (install on your computer; or use the program on the SH 2509 machines, where it is already installed)
- Try out the following tools for analyzing changing frequencies and other patterns of language in millions of books:
- Google Ngram Viewer
- HathiTrust Research Center Portal (requires creating a free account)
- Try out the following text analysis tools or suites of tools:
- WordTree
- LexHub.org (take a look at this new text analysis site to see if it's something that can be used for the class project in this course)
- History of concordances
- Beyond the concordance: Building blocks of text analysis:
- Counting (frequency)
- Co-occurrence (collocation)
- Clustering
- Comparison with reference corpus (as "corpus" is understood in field of corpus linguistics)
- Antconc
- corpus.byu.edu
- Related idea of "culturonomics" or "cultural analytics"--e.g.,
- Google Ngram Viewer
- Jean-Baptiste Michel, Erez Lieberman Aiden, et al., "Quantitative Analysis of Culture Using Millions of Digitized Books" (2011) (paywalled; UCSB students have free access from UCSB campus or Library Proxy server)
- HathiTrust Research Center Portal
- Currently leading-edge advanced methods of text analysis that build on top of the lower-level "building block" methods above:
- topic modeling
- social network analysis
- Other important supporting or complementary methods of text analysis:
- Parts-of-speech analysis (POS)
- Named entity recognition (NER)
- Sentiment analysis