The National Teaching Repository (NTR) has just won a prestigious national award for teaching and learning — the Collaborative Award for Teaching Excellence 2026. Good timing, then, to bring together two things I've been enjoying lately: being part of the NTR board, and playing with AI to solve problems.
I wanted to see what happened if I pointed some vibe-coding and some AI-assisted analysis at the repository itself. Could I surface patterns in the NTR that aren't obvious just from browsing it — the invisible web of who has worked with whom, and what the collective body of work is actually about? Two small activities, one feeding into the other.
Activity 1: Mapping co-author connections
The first idea was simple: go through the NTR's FigShare listing and map the links between authors, to see the inter-connectedness that has organically built up over the years.
The prompt I used was:
I would like to go through the https://figshare.edgehill.ac.uk/The_National_Teaching_Repository articles to show links between authors. Produce code to do this before generating the final code ask questions for clarity
The "ask questions for clarity before generating the final code" part matters — it's a small habit that saves a lot of wasted effort, and it meant the resulting code actually matched what I wanted rather than a guess at it.
 |
| co-author map |
The output was a co-author map — nodes for authors, edges for shared articles — showing at a glance who tends to cluster together and where the bridges between clusters sit.
The only hiccup was a genuinely minor one: one of the libraries the code needed wasn't mentioned in the setup instructions. I've fixed that in the repo itself, so if you want to run this yourself, the README has the fix for the missing import.
Code is here if you want to play with it: git@github.com:scottturnercanterbury/NTRAI.git
Activity 2: What is the NTR actually about?
With the edge data from Activity 1 already containing the titles of every piece in the repository, the obvious next question was: what are the themes? Not a deep dive into abstracts and descriptions — just titles — so treat this as indicative rather than exhaustive. Even so, it throws up some genuinely interesting patterns.
I asked for a proper thematic analysis, following Braun and Clarke's well-known method (V. Braun, V. Clarke, Using thematic analysis in psychology, Qualitative Research in Psychology, 3(2), 2006, pp. 77–101, DOI: 10.1191/1478088706qp063oa):
From the uploaded file using shared titles, carry out a thematic analysis. Before doing the analysis, please ask any questions you need, then do the analysis. Please use the steps in Braun and Clarke (V. Braun, V. Clarke, Using thematic analysis in psychology, Qualitative Research in Psychology, 3(2), 2006, pp. 77–101, DOI: 10.1191/1478088706qp063oa) to do this. Constraints Scope: All titles Depth of data: All available data Analytical lens: What are the themes in the repoistory this is data from https://figshare.edgehill.ac.uk/The_National_Teaching_Repository Target themes: Look for semantic themes and then provide a separate analysis of latent themes Please ask any clarification questions before starting the analysis.
Eight themes came out of it, covering all 324 titles:
- Designing, Assessing and Structuring the Curriculum (≈53 titles) — assessment design, feedback, module and curriculum development, employability.
- Digital, Technological and AI-Mediated Teaching (≈57 titles) — the largest cluster, spanning online/VR tools through to a fast-growing sub-cluster on generative AI in teaching.
- Equity, Belonging and Student Wellbeing (≈52 titles) — inclusive practice, decolonising the curriculum, mental health, personal tutoring.
- Active, Playful and Creative Pedagogy (≈19 titles) — gamification, escape rooms, zines and other creative/ludic methods.
- Discipline-Specific and Practice-Based Teaching (≈34 titles) — heavily health, nursing, bioscience and lab/fieldwork skills.
- Scholarly Identity, Recognition and the SoTL Community (≈45 titles) — Fellowship and NTF applications, SoTL identity and career development.
- Internationalisation and Cross-Border Partnership (≈27 titles) — international collaboration projects and support for international students.
- The Repository as Infrastructure (≈29 titles) — a reflexive cluster about the NTR itself: how to submit, how it's governed, its own history.
Two themes are worth a closer look. Digital, Technological and AI-Mediated Teaching is the single largest grouping — no surprise, but it's striking how much of that growth is very recent generative-AI content, from prompt templates to critique pieces on AI and racialised gender. And The Repository as Infrastructure is a nice reminder that a repository like this doesn't just accumulate content by accident — there's a whole meta-layer of guidance, governance and conference presentations keeping it alive, submitted by the same community that's building the co-author network in Activity 1.
So what?
Two different uses of AI, chained together: collect the data from the repository, visualise the links between authors, then hunt for themes in the titles.
There's plenty of refining still to do on Activity 1 — this was done quickly and should be seen as a starting point rather than a finished tool. The obvious issue is the same author sometimes showing up as two different nodes because of how their name was entered. And for Activity 2, capturing more information — abstracts, for instance — rather than just titles would sharpen the thematic analysis considerably.
Still, as a quick way of turning an award-winning repository into a map and a set of themes, it's a nice example of what a bit of vibe-coding and an afternoon can do.
Comments
Post a Comment