AI and metadata in the classroom: A work-integrated learning project
Bibliographic record
Abstract
Students in two undergraduate courses explored textual data and scholarly communication through a work-integrated learning project focused on journal metadata migration. They participated in workshops on manual metadata entry, AI prompt generation, and web scraping and scripting. Taking multiple approaches allowed students with diverse levels of digital literacy skills to critically engage with a real-world problem.In Team-GPT, students experimented with two artificial intelligence models, Claude Sonnet and GPT-4o, to convert HTML from a journal website into XML matching the Open Journal Systems schema. They broke the problem into smaller, manageable tasks, testing and refining reusable AI prompts. Along the way, they asked questions about journal practices and metadata challenges, gaining deeper insights into scholarly publishing. For a final assignment, each student created 18 metadata records using the AI-assisted workflow. These records will be evaluated alongside human-created metadata and outputs from a scripted approach to determine accuracy.This work-integrated learning project had substantial benefits for the journal, the library, and students. The journal editorial board will be able to make an informed decision about the migration to Open Journal Systems. Librarians, also the instructors for these courses, blended professional practice into pedagogy and made advances on a library publishing project. Students made meaningful contributions to the Open Access movement. We all practiced divergent problem-solving and continued to build informed opinions on the benefits and challenges of working with artificial intelligence.In this presentation, librarians and students will share our insights into how AI tools and metadata projects can be integrated into educational contexts. We will also discuss how work-integrated learning projects can effectively bridge pedagogy and practice, equipping students with critical skills in digital literacy, problem-solving, and scholarly communication.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.019 | 0.027 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.011 | 0.010 |
| Scholarly communication | 0.015 | 0.012 |
| Open science | 0.006 | 0.019 |
| Research integrity | 0.006 | 0.009 |
| Insufficient payload (model declined to judge) | 0.009 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".