For instructors
Using this book in a course
What the book assumes
The book is written for graduate students in the social sciences, including those returning to methods after some time away. The conceptual chapters assume no programming background. For the exercises, students need to run and adapt code; use Getting started and the primers to assess what preparation they need.
Course fit
The book is built for a semester-length graduate methods course on computational or AI-assisted social science research. It also works as:
- a research design course with computational examples (emphasize the theory chapters);
- a methods practicum where students build one project across the term (emphasize the exercise chapters, which chain into a single pipeline);
- a supplementary text in a data science course that needs the social-science research-design framing its main text lacks.
The structural logic
The book connects concepts with practice. Theory chapters (1, 2, 3, 5, 7, 9, 11, 12) develop the reasoning; exercise chapters (4, 6, 8, 10) apply it to a dataset each student builds from their own field’s literature.
Working with their own corpora gives students different results to compare and different decisions to defend. Ask them to explain how their data shaped those decisions. Use the shared setup guide and primers to troubleshoot technical problems across projects.
A possible fifteen-week shape
Each chapter’s lecture deck is linked below in PowerPoint and PDF. The decks include the book’s figures and key-concept recaps, speaker notes, and links to supporting materials. You can reorder, cut, and add your own material in the PowerPoint files. Figures reproduced from published sources carry a credit line and are included for instructional use.
| Weeks | Chapters and slide decks | Deliverable |
|---|---|---|
| 1–2 | Ch. 1, Introduction: PowerPoint · PDF; Ch. 2, AI-assisted research framework: PowerPoint · PDF | Project environment set up; research direction drafted |
| 3–4 | Ch. 3, Data as relational and process: PowerPoint · PDF; Ch. 4, Gathering literature: PowerPoint · PDF | Corpus retrieved, screened, documented; codebook and ERD |
| 5–7 | Ch. 5, From concepts to measures: PowerPoint · PDF; Ch. 6, Automated coding: PowerPoint · PDF | Coding pipeline: dictionary, LLM, classifier; validity audit |
| 8–10 | Ch. 7, Computational analysis and epistemic purposes: PowerPoint · PDF; Ch. 8, Applying computational methods: PowerPoint · PDF | Network, prediction, and embedding analyses |
| 11–12 | Ch. 9, Communicating research: PowerPoint · PDF; Ch. 10, Communicating your pipeline: PowerPoint · PDF | Integrative artifact with an uncertainty layer |
| 13–14 | Ch. 11, Ethics in computational and AI-assisted research: PowerPoint · PDF | Ethics review of the student’s own pipeline |
| 15 | Ch. 12, Conclusion: PowerPoint · PDF | Final presentation |
Assessment
Assign the chapter deliverables and use the Reflective Exercises for seminar discussion or short written responses. Ask students to explain the decisions behind their artifacts to assess their understanding.
For assignments that use AI, require the promptbook, promptlog, and validation evidence. Have students explain one disagreement, error, or revision and how it affected their analysis; documentation alone does not establish understanding.
Instructor materials
Everything on this site, the slide decks included, is free:
- Slide decks: one per chapter in PowerPoint and PDF, linked with the fifteen-week shape above.
- Chapter materials: hubs for Chapters 2–10 that bring together the relevant assignments, primers, examples, tools, and studies.
- CSS Empirical Studies Database: 122 studies with design-stage annotations. The theory-chapter hubs filter them for each Practice assignment.
- Worked notebooks and data: pre-executed, with a sample network dataset for the Chapter 8 exercises. Useful when a student’s own corpus is not ready in time.
- Getting started and the primers: shared preparation for students who need help setting up or using an unfamiliar technique.
A note on the studies database
Its coverage is uneven by design stage and thins after 2023. Ask students how those limits affect what they can infer about the field. Fewer communication annotations, for example, do not establish that published studies pay less attention to communication. Suggestions for additions are welcome through the errata page.
Engaging the book as scholarship rather than teaching from it? See For researchers.