QuerIA Dataset and Source Code (Pilot Edition)
Fuente:
Zenodo
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Recurso digital |
| Publicado: |
Zenodo
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866902266810728448 |
|---|---|
| author | Badenes-Olmedo, Carlos Eyzaguirre Barreda, Paul Andree |
| author_facet | Badenes-Olmedo, Carlos Eyzaguirre Barreda, Paul Andree |
| contents | <p>This repository contains the source code and anonymized pilot dataset for **QuerIA**, a system that generates and evaluates educational questions using large language models (LLMs) and Bloom-aligned contextual learning.</p> <p>The system was deployed at Universidad Politécnica de Madrid during the 2024–2025 academic year and used by students and instructors across 17 academic schools.</p> <h2><br>Repository Structure</h2> <h3>`/code/`</h3> <p>Contains the full implementation of QuerIA, including:</p> <p>- Semantic chunking strategy<br>- Prompt-based question generation (MCQs and OEQs)<br>- Automatic difficulty calibration based on Bloom’s Taxonomy<br>- Evaluation pipelines and feedback processing<br>- Docker and Ollama integration for local deployment</p> <p>See the `README.md` inside `/code/` for setup instructions.</p> <h3>`/data/`</h3> <p>Includes four anonymized CSV files:</p> <p>- `users.csv`: user profiles (school, program)<br>- `questions.csv`: generated questions with type, difficulty, context, and options<br>- `questionnaires.csv`: questionnaire configurations and metadata<br>- `feedback.csv`: user ratings and comments on generated questions</p> <p>All personal identifiers have been removed in compliance with GDPR and UPM ethics requirements.</p> <h2>Citation</h2> <p>If you use QuerIA or this dataset in your research, please cite the following article:</p> <blockquote> <p>> Badenes-Olmedo, C., & Eyzaguirre-Barreda, P. (2025). *QuerIA: Adaptive Question Generation and Evaluation in Higher Education Using Large Language Models and Contextual Learning*. (under review in Expert Systems with Applications) . [DOI and link pending publication</p> </blockquote> <p>Zenodo dataset:</p> <blockquote> <p>> Badenes-Olmedo, C., & Eyzaguirre-Barreda, P. (2025). *QuerIA: Source Code and Pilot Dataset* [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.16641780">https://doi.org/10.5281/zenodo.16641780</a></p> </blockquote> <h2><br>Authors</h2> <p>- Carlos Badenes-Olmedo — Universidad Politécnica de Madrid <br>- Paul Eyzaguirre-Barreda — Universidad Politécnica de Madrid</p> <h2><br>License</h2> <p>This project is licensed under the MIT License for the code, and a CC BY 4.0 License for the dataset.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_16641780 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | QuerIA Dataset and Source Code (Pilot Edition) Badenes-Olmedo, Carlos Eyzaguirre Barreda, Paul Andree question generation Bloom's taxonomy educational technology large language models <p>This repository contains the source code and anonymized pilot dataset for **QuerIA**, a system that generates and evaluates educational questions using large language models (LLMs) and Bloom-aligned contextual learning.</p> <p>The system was deployed at Universidad Politécnica de Madrid during the 2024–2025 academic year and used by students and instructors across 17 academic schools.</p> <h2><br>Repository Structure</h2> <h3>`/code/`</h3> <p>Contains the full implementation of QuerIA, including:</p> <p>- Semantic chunking strategy<br>- Prompt-based question generation (MCQs and OEQs)<br>- Automatic difficulty calibration based on Bloom’s Taxonomy<br>- Evaluation pipelines and feedback processing<br>- Docker and Ollama integration for local deployment</p> <p>See the `README.md` inside `/code/` for setup instructions.</p> <h3>`/data/`</h3> <p>Includes four anonymized CSV files:</p> <p>- `users.csv`: user profiles (school, program)<br>- `questions.csv`: generated questions with type, difficulty, context, and options<br>- `questionnaires.csv`: questionnaire configurations and metadata<br>- `feedback.csv`: user ratings and comments on generated questions</p> <p>All personal identifiers have been removed in compliance with GDPR and UPM ethics requirements.</p> <h2>Citation</h2> <p>If you use QuerIA or this dataset in your research, please cite the following article:</p> <blockquote> <p>> Badenes-Olmedo, C., & Eyzaguirre-Barreda, P. (2025). *QuerIA: Adaptive Question Generation and Evaluation in Higher Education Using Large Language Models and Contextual Learning*. (under review in Expert Systems with Applications) . [DOI and link pending publication</p> </blockquote> <p>Zenodo dataset:</p> <blockquote> <p>> Badenes-Olmedo, C., & Eyzaguirre-Barreda, P. (2025). *QuerIA: Source Code and Pilot Dataset* [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.16641780">https://doi.org/10.5281/zenodo.16641780</a></p> </blockquote> <h2><br>Authors</h2> <p>- Carlos Badenes-Olmedo — Universidad Politécnica de Madrid <br>- Paul Eyzaguirre-Barreda — Universidad Politécnica de Madrid</p> <h2><br>License</h2> <p>This project is licensed under the MIT License for the code, and a CC BY 4.0 License for the dataset.</p> |
| title | QuerIA Dataset and Source Code (Pilot Edition) |
| topic | question generation Bloom's taxonomy educational technology large language models |
| url | https://doi.org/10.5281/zenodo.16641780 |