Developing a correlation matrix to map Program Educational Objectives with Mission Statements using SBERT and Augmentation Techniques
DOI:
https://doi.org/10.22399/ijcesen.2923Keywords:
Finite Element Simulation, Homogenization, Subroutine, CardboardAbstract
To ensure coherence between departmental goals and particular program objectives, it is crucial for engineering education to align program education objectives (PEOs) with departmental mission statements. This mapping is done manually, which can be insignificant, time consuming and biased. For the institution to meet its objectives and accreditation requirements, these components must be aligned. With the use of advanced Natural Language Processing (NLP) techniques, particularly sentence-based BERT (SBERT), this study suggests an automated way to map PEOs with departmental mission statements. Since the dataset was limited, we enhanced it by applying text augmentation techniques like synonym replacement, random insertion, deletion, and text shuffling. The dataset was obtained from the Department of Civil Engineering at B.S. Abdur Rahman Crescent Institute of Science and Technology. Cosine similarity is used for fine-tuning SBERT model. It determines the semantic similarity score between PEO and departmental missions and classifies them into high, medium, low, or no similarity based on a threshold values set by experts. Levels of similarity and alternative PEO descriptions for each level of similarity are justified using a rubric system which was created to validate the mapping. The findings show that SBERT can provide a transparent and objective framework for curriculum planning and educational assessment by accurately capturing the semantic relationship between PEOs and departmental mission statements.
References
[1] Nguyen, M. H., Pham, H. T., Ha, H. M., Le, N. Q. H., & Jo, J. (2025). Technology Mapping with Large Language Models. arXiv preprint arXiv:2501.15120.
[2] Opitz, J., & Frank, A. (2022). SBERT studies meaning representations: Decomposing sentence embeddings into explainable semantic features. arXiv preprint arXiv:2206.07023.
[3] Wang, B., & Kuo, C. C. J. (2020). Sbert-wk: A sentence embedding method by dissecting bert-based word models. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2146-2157.
[4] Pijeira‐Díaz, H. J., Subramanya, S., van de Pol, J., & de Bruin, A. (2024). Evaluating Sentence‐BERT‐powered learning analytics for automated assessment of students' causal diagrams. Journal of Computer Assisted Learning, 40(6), 2667-2680.
[5] Keeling, R. (2004). Learning outcomes in higher education. Change: The Magazine of Higher Learning, 36(3), 43-49.
[6] Waghid, Y. (2004). Philosophy of education in the democratic and multi-sectoral South African context. South African Journal of Education, 24(2), 77-82.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering

This work is licensed under a Creative Commons Attribution 4.0 International License.