Generative-AI Assisted Feedback Provisioning for Project-Based Learning in CS Courses
Bibliographic record
Abstract
Abstract Project-Based Learning (PBL) is a pedagogical method that combines theory and practice by involving students in real-world challenges. Continuous feedback is crucial in PBL, guiding students to improve their methods and foster progressive thinking. However, PBL faces challenges in widespread adoption due to the time and expertise needed for effective feedback, especially with increasing student numbers. This paper presents a novel approach using Generative AI, specifically an enhanced ChatGPT, to provide effective PBL feedback. For an undergraduate Web Technology course, we integrated three strategies: 1) fine-tuning ChatGPT with feedback from various sources; 2) using additional course-specific information for context; 3) incorporating external services for specialized feedback. We developed a tool that implements these strategies both independently and in a combined fashion. We assessed the effectiveness of the tool we developed by conducting user studies, which confirmed that this tool improves the quality of feedback as compared with general-purpose ChatGPT. By acquiring and retaining knowledge from different sources, our approach offers a powerful component for implementing PBL on a large scale.
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 | 0.006 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.003 |
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".