Introduction to Text Analysis from Close Reading to Machine Learning

Academic Program: 

Instructor: Jessie Labov, Levente Littvay, Marsha Siefert

Credits: 2.0

Course description: 

This course will provide an overview and introduction to the varied practices of text analysis, survey how text analysis work in different disciplines, and ask critical questions about the larger impact of data-driven research. We will begin with the heuristics of reading and interpreting texts, and look at the strategies and languages that have evolved in schools of textual criticism, but then focus specifically on recent methodologies of reading with computational tools. The goal of this introductory course is for each student to find an approach to his or her own discipline and research area which employs a range of strategies for textual analysis, and to understand the scope, value and limitations of those strategies. 

No prior knowledge of programming or query languages is necessary, but students will gain basic skills in using web-based tools (e.g., Voyant, Juxta, TaPOR, Mallet), as well as an orientation on the different programming languages that are used for text analysis (R, Python).

Learning outcomes: 

• categorize and compare different approaches to text analysis in a range of disciplines
• distinguish between different metadata standards and protocols
• mark up a document with TEI or other mark-up alternatives
• describe the linguistic features relevant to the natural language processing pipeline
• construct a discipline-specific argument using the results of a text analysis
• relate these data-driven and computational techniques to other quantitative and qualitative approaches to textual analysis