The text analysis resources here cover topics such as installing computer programming languages (like R and Python), running exploratory scripts of word tokenizations and counts, and more advanced approaches like topic modeling and word embedding models.
Getting Started
- Finding data sets for text analysis
- “Where to Start” by Ted Underwood
- Text analysis introduction from ‘‘Tooling Up for Digital Humanities’’
- “Natural Language Processing with Deep Learning” from Stanford
- “Text Mining with R: A Tidy Approach” textbook by Julia Silge and David Robinson
- “Computational Text Analysis for Social Science” by Brendan O’Connor et al.
Python
- ‘‘Python Programming for the Humanities’’ by Folgert Karsdorp
- “Python for Informatics” by Charles Severance, an applied but comprehensive introductory Python text with sections on text parsing
- Download and install Python
- Download and install PyCharm, an Integrated Development Environment (IDE) for Python
- Download and install IPython, an interactive shell for Python
- The Hitchhiker’s Guide to Python
- Neal Caren’s tutorials on Python and text analysis
- Codeacademy for Python
- Dataquest for Python, a Data Science Approach to Python
- Google’s Python Class
- Machine Learning with Sci-Kit Learn, video tutorials for machine learning in python with the Sci-Kit Learn Package
- Natural Language Processing in Python
- Web-Scraping with Python
- Laura K. Nelson’s Python Text Analysis Course
- Python for Everyone, an open source Python textbook with exercises
- Practice Python, Beginner Python Exercises
R
- Matthew Jockers, Text Analysis With R for Students of Literature (PDF available for download via the NEU Library)
- Download and install R
- Download and install RStudio, an Integrated Development Environment (IDE) for R
- RSeek, a search tool for finding resources on R
- Simple data types in R
- Ben Schmidt’s Humanities Data Analysis class
- Managing and Manipulating Data in R
- Chris Bail’s Text as Data R Course
- A Light Introduction to Text Analysis in R, an introduction and overview of text analysis tools in R
- Data Science Specialization Course, a broad course in R covering multiple data science techniques like statistical inference, machine learning, regression models, exploratory analysis, and others
- Nick Beauchamp’s Computational Statistics in R course
Topic Modeling
- JDH’s Special Issue on Topic Modeling (2012)
- Megan R. Brett’s “Basic Introduction” (conceptual)
- Ben Schmidt’s article about Latent Dirichlet allocation’s (LDA’s) limitations
- “Topic modeling made just simple enough” by Ted Underwood
- “Guided Tour,” by Scott Weingart, a comprehensive guide with many links
- MALLET, an open-source and Java-based Latent Dirichlet allocation (LDA) package
- Stanford Topic Modeling Toolbox (an alternative to MALLET)
Word Embedding Models
- The Women Writers Vector Toolkit
- Ben Schmidt’s Blog Post on Vector Space Models
- which links to his R package wrapping word2vec (word2vec is written in C)
Other Text Analysis Tools and Resources
- Voyant Tools, a simple web-based analysis and visualization tool
- Lexos, a tool for scrubbing, chunking, and tokenizing text, in addition to performing modest analysis and visualizing clusters
- Scott Kleinman’s blog post on “How to Create Topic Clouds with Lexos”
- Laurence Anthony’s AntConc, a GUI concordancing and text analysis toolkit
- CasualConc, a Mac OSX-native toolkit (AntConc’s Mac version is ported from the PC, and has some bugs)
- David McClure’s TextPlot, a Python package that produces force-directed network of words in a text, the nodes of which are clustered using estimated kernel densities
- Bookworm, a customizable corpus trend visualization tool
- Word Tree, a tool that creates word trees from a block of text
- Justin Grimmer’s course on applied text analysis (pdf)
- Stanford CS224N: NLP with Deep Learning (video)