INFO 3350
Text Mining History and Literature
The class will introduce methods for computer-assisted analysis of historical and literary text collections. It will cover corpus curation, representing text as data, building statistical models from text, and interpreting quantitative results. The class will also reflect on how computational methods fit with existing practices in the humanities, and how we can use models as complements to our own interpretations. Following the course, students will be able to assist faculty in quantitative and computational humanities scholarship.
Topics
- Describe and evaluate major existing results in quantitative humanities research.
- Recognize, explain, evaluate, and implement standard techniques for the use of text as data.
- Create reliable, compelling, data-driven humanities research reports that apply suitable text-mining methods to existing humanities questions.
- Identify and analyze historical, ethical, and epistemic limitations of existing and potential textual corpora.
- For graduate students: Evaluate and adapt text-mining methods to current research problems relevant to the student's work.
- For graduate students: Analyze, evaluate, and present current research findings in computational text analysis.
Official roster learning outcomes
Prerequisites & course information
INFO 2950 or permission of instructor.
Sources
- Course catalogue ↗2026-2027