Digital Humanities B (Language Processing and Information Retrieval)
All Digital Humanities courses
Course schedule
In fall–winter 2026, all classes meet on Tuesdays, 14:40–16:10, in DH Lab B307. Lab computers are available.
| Class | Date | Topic |
|---|---|---|
| 1 | Overview, introductions, and a text investigation | |
| 2 | Classifying movement in context | |
| 3 | Searching by lemma and pattern | |
| 4 | Comparing authors and models | |
| No class | ||
| 5 | Checking an agent’s evidence | |
| 6 | Noun–particle–verb combinations with dependencies | |
| 7 | Building and evaluating a classifier for movement expressions |
In classes 1–5, students investigate movement in Akutagawa Ryūnosuke’s 「蜘蛛の糸」 (Kumo no ito, “The Spider’s Thread”) and other works as one continuing study, reported in an assignment set in class 5. Topics without a link are planned; each class page is linked when it is published.
- Course guide: assessment, attendance, submissions, and the final project.
- Course resources: command and classification references, terms and ideas, how-to guides, the movement worksheet, the NER comparison, and the sources and tools used in the course.
Assignments and submission
| Assignment | Deadline | Where to submit |
|---|---|---|
| Evidence assignment | Before class 6 starts (November 17, 14:40) | Submission page (campus network only) |
The submission page opens only on the campus network. If you are off campus, submit from a lab PC before class 6 starts.
Course purpose
This course develops practical skills in natural language processing (NLP) and information retrieval for humanities research. Using modern Japanese and English literature, students compare dictionary and rule-based methods, trained models, and generative LLMs, and evaluate their results, limitations, computational requirements, and reproducibility.
Learning goals
- Prepare and search corpora with metadata.
- Write basic Python text-processing programs and create and interpret visualizations.
- Apply text search, topic models, named entity recognition (NER), and document classification.
- Compare dictionary and rule-based methods, trained models such as GLiNER, and generative large language models (LLMs) using source texts and shared evaluation criteria.
- Produce a reproducible analysis notebook or program, with an explanation of the research question, method, evidence, and limitations.