Semantic similarity between curricular aspects of an engineering program and national and international quality benchmarks
DOI:
https://doi.org/10.26507/paper.4259Keywords:
High Quality Accreditation, Natural Language Processing, Semantic Similarity, International StandardsAbstract
This paper analyzes the semantic coherence between the curricular aspects of an engineering program and the quality benchmarks established by the National Accreditation Council (CNA), EUR-ACE, and ARCUSUR, using natural language processing techniques. Semantic embeddings were generated using the SBERT model, and automatic paraphrasing models based on transformers (Vamsi/T5 and milyiyo) were applied to measure the semantic similarity between institutional texts and accreditation criteria. Interventions were proposed on institutional texts to increase their alignment with the benchmarks, incorporating frequent terms extracted from quality standards. The results show a significant improvement in semantic similarity, particularly with CNA and ARCUSUR benchmarks, thus validating the usefulness of the proposed approach. This methodology strengthens self-assessment and accreditation processes, offering a replicable strategy for other higher education institutions interested in evaluating and optimizing their curricular documents from a quantitative, evidence-based perspective.
Author Biography
Alveiro Rosado Gómez, Universidad Francisco de Paula Santander
Docente Tiempo Completo
Mg Gestión Aplicación y Desarrollo de Software
Investigador grupo de investigación GITYD
References
Almeida, F., & Xexéo, G. (2019). Word Embeddings: A Survey. arXiv, 1-10.
Elekes, Á., Schäler, M., & Böhm, K. (2017). On the Various Semantics of Similarity in Word Embedding Models. International Conference on Big Data (págs. 2655-2664). Boston: IEEE. https://doi.org/10.1109/JCDL.2017.7991568
Ferreira, R., Cavalcanti, G. D., Freitas, F., Lins, R. D., Simske, S. J., & Riss, M. (2017). Combining sentence similarities measures to identify paraphrases. Computer Speech & Language. https://doi.org/10.1016/j.csl.2017.07.002
Kenter, T., & de Rijke, M. (2015). Short Text Similarity with Word Embeddings. International Conference on Information and Knowledge Management (págs. 1411-1420). Melbourne: ACM. https://doi.org/10.1145/2806416.2806475
Peláez, L. E., Parra, J. A., Delgado, I. A., & Ovalle, D. L. (2020). La acreditación internacional de programas de ingeniería y su impacto en la calidad desde los resultados de aprendizaje. EIEI ACOFI.
Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv. https://doi.org/10.18653/v1/D19-1410
Triana, M. Y., Forero García, E. F., & Montenegro Narváez, C. E. (2018). Estrategias de acreditación para programas de ingeniería electrónica bajo criterios internacionales ARCUSUR. EIEI ACOFI.
Verma, D., Lal, Y. K., Sinha, S., Van Durme, B., & Poliak, A. (2023). Evaluating Paraphrastic Robustness in Textual Entailment Models. arXiv. https://doi.org/10.18653/v1/2023.acl-short.76
Wang, C., Li, M., & Smola, A. J. (2019). Language Models with Transformers. arXiv.
How to Cite
Downloads
Downloads
Published
Proceeding
Section
License
Copyright (c) 2025 Asociación Colombiana de Facultades de Ingeniería - ACOFI
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
| Article metrics | |
|---|---|
| Abstract views | |
| Galley vies | |
| PDF Views | |
| HTML views | |
| Other views | |
