Open Educational Resources
Document Type
Lesson Plan
Publication Date
2026
Abstract
This 4 week module is designed for Data Analysis, Data Visualization, and Digital Humanities courses at the MA/MS or advanced 400-level undergraduate level. It introduces students to textual analysis with topic modeling and requires a solid foundation in Python. The module uses Gensim and a Colab notebook to introduce a standard text analysis workflow used in Digital Humanities, archival research, and exploratory data analysis.
Students build a topic model describing 19,000 CUNY Graduate Center dissertations and theses. They work with an unexplored dataset to load and explore the data, prepare the corpus, train and evaluate a topic model, and interpret, visualize, and explore the results. Students develop research questions that the tool and data can answer, while also identifying questions that the tool cannot answer. The assignment emphasizes preprocessing, stopwords, topic size, coherence scores, and using critical thinking to assess the relationship between model output and human interpretation. Ultimately, the goal is for students to reflect on the strengths and limitations of the tool and the assumptions baked into it.
The module includes a weekly lesson plan, learning objectives, an assignment description, and code resources on Github.
The lesson can be adapted to other meaningful textual corpora. Instructors might work with student capstone projects, institutional archives, historical course schedules, or other campus collections, and are encouraged to work with archivists or librarians to identify appropriate datasets.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
