Last updated: Sep 28, 2026

DHG 502 Course Syllabus

Digital Approaches in Historical Research
Term 1, 2026–2027
MA in Digital History in Global Asia · Core · 3 credits

Seminar: Mon, 6:30–9:30 pm (MPL 1201, Lingnan@West Kowloon Campus; 19 Oct cancelled; dates in the schedule)

Instructor: Maciej Kurzynski 馬傑 (maciej.kurzynski[at]ln.edu.hk)
Office hours: Tue 3:00–5:00 pm and Fri 10:00 am–12:00 pm, HSH G06, or by appointment
Language of Instruction: English

Digital Approaches in Historical Research

Course Description

This course familiarizes students with the approaches, theories, and tools of digital historical scholarship. It is designed to develop their skills as thinkers, writers, and creators of historical narratives about Global Asia, enabling them to support historical arguments with digital evidence. Through a practical source-to-data workflow, students learn to turn historical texts and images into documented datasets; work with corpora, networks, structured data, and databases; annotate cultural-heritage images; and evaluate computational results. Case studies address urban life, heritage, mobility, networks, race, class, and gender, as well as the ways digital technologies are changing research and presentation in museums, libraries, and archives. The course also examines large language models and AI coding assistants as research tools. Prior programming experience is not required; prepared examples and guided exercises allow students to focus on historical reasoning, source criticism, validation, and interpretation rather than code complexity.

Aims

This course aims to train MA students to examine the approaches, theories, and tools of digital historical scholarship; investigate their connections with established historical methods; and apply them independently to questions about Global Asia. Students will work with Asian historical sources, archives, and databases; consider digital forms of research and public presentation; and evaluate critically how new technologies are changing the discipline. They will learn to write, debug, and evaluate research code with AI coding assistants while remaining attentive to methodological limits and ethical challenges, and will design a project that brings digital methods to bear on a historical problem.

Learning Outcomes

Upon completion of this course, students should be able to:

Identify major approaches, theories, and tools in digital historical scholarship and relate them to established historical methods
Explain how digital technologies affect historical research and presentation in museums, libraries, and archives
Turn historical texts and images into documented, structured research data
Apply appropriate computational methods to historical research questions
Use AI-assisted coding tools to write, debug, test, and document research code
Evaluate the benefits, limitations, and ethical challenges of computational and AI-generated results against historical evidence
Design and communicate a reproducible project that combines digital methods with historical inquiry

Language of Instruction

The course is conducted in English. Assigned readings may be in English or Chinese. Historical sources for assignments and the final project may be in English, Chinese, or other languages relevant to the student’s research. All assessed work must be completed and submitted in English.

Preliminary Setup

Please complete the following before the first seminar. MA students must use their own computers; no shared classroom machines will be provided.

Create a GitHub account.
Collect your API key at keyreg.qhchina.org (class code: dhg502). Do not put the key in a repository or share it with others.
On your laptop, install Python, Visual Studio Code (VS Code), and then OpenCode. Step-by-step: how to set up an AI coding agent. If you cannot install locally, use GitHub Codespaces instead (same page): create a new repository from the course template and work in the browser.
Install or update Google Chrome or Microsoft Edge for the image-annotation lab.

Week 1 sets up the research environment (GitHub, VS Code, OpenCode, and AI coding assistants). Bring a laptop with the software already installed, or use GitHub Codespaces in the browser if you cannot install locally — see the setup page.

Assessment

Students’ progress towards the learning outcomes will be measured by means of:

Component	Weight
Class participation	15%
Assignments	30%
In-class presentation	15%
Project proposal	10%
Final project	30%

Requirements and marking criteria are available on the assignments page.

Grading scale: A 85%–100%; A− 80%–84%; B+ 75%–79%; B 70%–74%; B− 65%–69%; C+ 60%–64%; C 55%–59%; C− 50%–54%; D+ 45%–49%; D 40%–44%; F 0%–39%

Attendance Policy

Students are expected to attend all seminars. One unexplained absence is permitted, no questions asked. Unexplained absences will not impact the final grade by more than 15% (the maximum you can get for class participation), unless a student misses more than four (4) meetings, in which case there will be insufficient evidence of participation to award a passing grade. Every unexplained absence (beyond the one everyone gets for free) will remove 10% from the participation component (which equals 1.5% of the final grade). For example, if you are absent two times without explanation (in addition to the one no-questions-asked absence granted to everyone), you will receive 100% − 20% = 80% of the total possible contribution from participation, which amounts to 80% × 15% = 12% of the final grade. Remember to come to class on time and prepared.

AI Policy

This course teaches agentic coding, and students are expected to use AI coding assistants for research code. All use must be documented according to the assignment instructions. Students remain responsible for every claim, citation, line of code, and analytical decision they submit, and must be able to explain their work. AI-generated analytical prose may not be submitted as the student’s own work. Do not upload confidential, sensitive, or unpublished sources to an external AI service without permission.

Course Design

1. Seminars. Weekly seminars combine conceptual discussion with supervised hands-on practice. The recurring workflow is source → documented data → method → validation → historical interpretation. Starter materials and a short technical glossary will be provided.

Examples of in-class tasks. Starting in Week 6 (12 Oct), each seminar includes a specific hands-on task that everyone works on together. Examples of such tasks:

Use the Multimedia Information System (offered by the Hong Kong Public Libraries) to find photos and articles about old Hong Kong. You can focus on a particularly famous place (Kai Tak Airport, Kowloon Walled City, e.g.). Choose one or two articles and summarize them, including the photographs you found. Offer your analysis of the platform: how does it facilitate digital scholarship?
Go to one of the many Hong Kong museums. What are the digital tools that the museum curators used to welcome the audience? Write a 1,000-word report of your visit.
Given the provided dataset, train a topic model and identify some of the most important topics. Analyze them: what are these topics about? Is your result replicable? What does the topic distribution tell you about the dataset?

2. Assignments. Assignment 0 is ungraded. Two graded assignments, a project proposal, and the final project are submitted through Moodle. Instructions are linked in the schedule.

3. In-class presentation. Students work in groups of up to three. Each group presents one academic paper during one of five presentation sessions (Weeks 4, 6, 8, 10, and 12) and leads the discussion. Every group member must speak, and the group receives a shared mark. The paper may be in English or Chinese, but the presentation and discussion must be in English.

4. Final project. Students work individually or in groups of up to three, apply one or more course methods to a historical question, and submit a reproducible GitHub repository and an English report. Full requirements and marking criteria are on the assignments page.

Class Schedule

Week	Date	Topic	Class Content and Readings	Notes
1	7 Sep	Introduction	Class content Digital history: research questions, source criticism, and the source-to-data workflow Guiding question: What does it mean to think historically about the digital and digitally about the historical? Hands-on: Git, GitHub, VS Code, OpenCode, and carefully guided agentic coding Readings Mats Fridlund, “A Middle Way between Normal and Paradigmatic Digital Historical Research,” in Digital Histories: Emergent Approaches within the New Digital History (2020)	Notes
2	14 Sep	Sources as Data: Labor, Context, and Risk	Class content Files as data; binary, Unicode, and UTF-8; CSV and JSON by example Metadata, provenance, sampling, archival silences, copyright, privacy, and research data Readings Billy Perrigo, “OpenAI Used Kenyan Workers on Less Than $2 Per Hour to Make ChatGPT Less Toxic,” TIME, 18 January 2023 Johan Jarlbrink, “All the Work that Makes It Work: Digital Methods and Manual Labour,” in Digital Histories: Emergent Approaches within the New Digital History (2020) Roopika Risam, New Digital Worlds: Postcolonial Digital Humanities in Theory, Praxis, and Pedagogy (Northwestern UP, 2018), Introduction (optional) Lara Putnam, “The Transnational and the Text-Searchable: Digitized Sources and the Shadows They Cast,” American Historical Review 121, no. 3 (2016) (optional) Catherine D’Ignazio and Lauren F. Klein, Data Feminism (MIT Press, 2020), Chapter 6, “The Numbers Don’t Speak for Themselves” (open access)	Notes
3	21 Sep	Building a Corpus	Class content Research questions, selection and sampling; regex (RegexOne, Regex ABCs for Chinese); tokenization; cleaning; stopwords; transformation logs Brief demonstration: the Chinese Text Project as a digital source and corpus platform Readings Jo Guldi, The Dangerous Art of Text Mining: A Methodology for Digital History, Introduction and Chapter 1 (optional) Donald Sturgeon, “Digitizing Premodern Text with the Chinese Text Project,” Journal of Chinese History 4, no. 2 (2020) (optional) Cécile Armand, “ReOrienting Digital History: New Frontiers in Chinese Studies,” Journal of Digital History 3, no. 3 (2024, open access), selected sections	Notes
	23 Sep	Assignment 0 (not graded) due, 9:00 am
4	28 Sep	Collocations	Class content Collocation as a method; contingency tables; Fisher’s exact test; effect, significance, and historical interpretation Readings Stefan Evert, “Corpora and Collocations”	Notes Slides
4	28 Sep	Presentation	One paper chosen by your group on collocations, keyword analysis, or corpus-based text mining in historical research
5	5 Oct	Historical Network Analysis	Class content Nodes, edges, and historical relationships; data formats; centrality and community Entity identity, tabular edge lists, missing relationships, and uncertainty Working with historical datasets (e.g. CBDB); Gephi, Palladio, and Python Readings Scott B. Weingart, “Demystifying Networks, Parts I & II” Ruth Ahnert, Sebastian E. Ahnert, Catherine Nicole Coleman, and Scott B. Weingart, The Network Turn: Changing Perspectives in the Humanities (Cambridge Elements, 2020; open access) Hilde De Weerdt, Brent Ho, Allon Wagner, Qiao Jiyan, and Chu Mingkin, “Is There a Faction in This List?,” Journal of Chinese History 4 (2020) (optional) Henrike Rudolph and Song Chen, eds., “Beyond Guanxi: Chinese Historical Networks,” Journal of Historical Network Research 5 (2021)	Slides
	13 Oct	Assignment 1 due, 9:00 am
6	12 Oct	OCR, HTR, and Multimodal Transcription	Class content From printed and handwritten page images to text; layout, transcription, normalization, and correction Validation with human ground truth; character and word error rates; why plausible text may still be wrong Readings Maria Levchenko, “Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities” (2025), Introduction and Conclusion Chung Yan Hon Michael and Donghyeok Choi, “Fine-Tuning Vision–Language Models as OCR Systems for Low-Resource Languages: A Case Study of Manchu”, Computational Humanities Research 2 (2026): e20 Lab guide Laura Turner O’Hara, “Cleaning OCR’d Text with Regular Expressions” (selected sections)	Notes Slides
6	12 Oct	Presentation	One paper chosen by your group on OCR, handwritten text recognition, or the construction and evaluation of transcribed historical corpora
	19 Oct	No class (Day following Chung Yeung Festival)
7	26 Oct	Topic Modeling	Class content LDA; what is a “topic”?; model choices, close reading, and interpretive limits Conceptual comparison with embedding-based document clustering Readings Ted Underwood, “Topic Modeling Made Just Simple Enough” (2012) (optional) David M. Blei, “Probabilistic Topic Models” (2012)	Notes Slides
8	2 Nov	Cultural Heritage and Image Annotation	Class content Interpretation, preservation, reconstruction, and authenticity in the digital representation of cultural heritage; digital museum, library, and archive platforms (Hong Kong Heritage Museum, Hong Kong Palace Museum) Computer vision and “distant viewing”: what computational image analysis can and cannot “see,” and how it relates to manual annotation; 3D and virtual reconstructions as case studies in historical accuracy (critique only) Hands-on: use IMMARKUS to annotate regions in an East Asian historical image; inspect CSV and JSON-LD exports Readings Freeman Tilden, Interpreting Our Heritage, Introduction Taylor Arnold and Lauren Tilton, Distant Viewing: Computational Exploration of Digital Images (MIT Press, 2023; open access), Chapter 1, “Distant Viewing: Theory” Sarah Kenderdine, “Radical Intangibles: Materializing the Ephemeral,” Museum Anthropology Review 19, no. 2 (2024), selected sections (optional) Hilde De Weerdt et al., “Contextual Semantic Text and Image Annotation in the MARKUS Environment”, Digital Humanities Quarterly 19, no. 4 (2025), selected sections (optional) Fiona Cameron and Sarah Kenderdine, eds., Theorizing Digital Cultural Heritage: A Critical Discourse (MIT Press, 2007) Lab guide “Reading Digital Historical Sources with IIIF and Web Annotation—An IMMARKUS Hands-on”
8	2 Nov	Presentation	One paper chosen by your group on digital cultural heritage, image annotation, or computational image analysis (“distant viewing”)
	9 Nov	Assignment 2 due, 9:00 am
9	9 Nov	Conceptual History and Word Vectors	Class content What is meaning? Word vectors and cosine similarity Static and contextual embeddings; conceptual change and historical bias Readings Daniel Jurafsky and James H. Martin, “Vector Semantics and Embeddings” Austin C. Kozlowski, Matt Taddy, and James A. Evans, “The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings,” American Sociological Review 84, no. 5 (2019) (optional) William L. Hamilton, Jure Leskovec, and Dan Jurafsky, “Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change” (ACL 2016)
10	16 Nov	Databases and Structured Historical Data	Class content Schemas, records, fields, data types, identifiers, and one-to-many relationships CSV versus JSON; SQLite and introductory SQL; why a database is not a spreadsheet In-class: build and query a small database of historical people, sources, and events Readings Matthew Lincoln, “Reshaping JSON with jq” (selected sections)
10	16 Nov	Presentation	One paper chosen by your group on historical databases, data modeling, or research built on structured historical datasets
	20 Nov	Final Project Proposal due, 9:00 am
11	23 Nov	LLM Workflows for Historical Sources	Class content From BERT to GPT; next-token probability, context, tokens, and APIs JSON-schema structured outputs; information and entity extraction; source-linked semantic search and retrieval-augmented generation (RAG) Hands-on: extract a small batch, check it against human-coded examples, and record errors Readings Ted Underwood, Laura K. Nelson, and Matthew Wilkens, “Can Language Models Represent the Past without Anachronism?” Thierry Poibeau, “What Do Historical Language Models Model?” (optional) Maximilian Hindermann et al., “The RISE Humanities Data Benchmark: A Framework for Evaluating Large Language Models for Humanities Tasks” (2026), Introduction (optional) A recent piece treating generative AI as an object of historical source criticism, including documented failure modes such as models “over-historicizing” transcriptions with anachronistic archaic characters (to be selected from current literature)
12	30 Nov	Data Visualization and Reproducibility	Class content Visualization as argument; charts, timelines, and network diagrams; moving between aggregate patterns and close reading Data dictionaries, dependencies, transformation logs, README files, re-run checks, and responsible sharing Readings Carl T. Bergstrom and Jevin D. West, Calling Bullshit: The Art of Skepticism in a Data-Driven World, Chapters 4 (“Causality”) and 5 (“Numbers and Nonsense”) Toby Burrows, “Reproducibility, Verifiability, and Computational Historical Research” (2023), selected sections (optional) An article from the Journal of Digital History special issue “ReOrienting Digital History” (2024) as an Asia-specific visualization case that doubles as a reproducibility exemplar (code and data layers published with the narrative)
12	30 Nov	Presentation	One paper chosen by your group on data visualization as historical argument, or on reproducibility and verifiability in computational historical research
	7 Dec	Final project due, 9:00 am

Important Notes

Students are expected to spend a total of 9 hours (i.e. 3 hours of class contact and 6 hours of personal study) per week to achieve the course learning outcomes.
Students shall be aware of the University regulations about dishonest practice in course work, tests and examinations, and the possible consequences as stipulated in the Regulations Governing University Examinations. In particular, plagiarism, being a kind of dishonest practice, is “the presentation of another person’s work without proper acknowledgement of the source, including exact phrases, or summarised ideas, or even footnotes/citations, whether protected by copyright or not, as the student’s own work.” Students are required to strictly follow university regulations governing academic integrity and honesty.
To enhance students’ understanding of plagiarism, a mini-course “Online Tutorial on Plagiarism Awareness” is available on https://pla.ln.edu.hk/.
Ethical data acquisition: Scraping, bulk downloading, or other automated collection must be approved and supervised by the instructor. Students must follow the provider’s rules and technical limits and use official download tools when available. Unauthorized collection cannot be used for assessed work.