Explainable AI for Code-Switching Assessment in Philippine University Admissions

Authors

  • Meshel B. Balijon

    College of Public Governance, Safety and Sustainability, Cebu Normal University, Cebu 6000, Philippines

DOI:

https://doi.org/10.30564/fls.v7i11.11376
Received: 30 July 2025 | Revised: 19 August 2025 | Accepted: 1 September 2025 | Published Online: 23 October 2025

Abstract

Traditional educational admission systems rely heavily on cognitive metrics, while existing AI approaches present critical limitations: black-box decision-making without interpretable reasoning, an inability to assess multilingual competence, and a failure to model nuanced human judgment in educational contexts. Deep learning and ensemble methods lack the transparency required for accountable admissions, particularly in culturally diverse settings where linguistic factors significantly influence academic success. This study addresses these gaps through a novel Fuzzy-Genetic Algorithm framework for admission decisions in licensure-based programs. The system integrates fuzzy logic and genetic algorithms to assess cognitive (IQ, aptitude), behavioral (study habits, reading comprehension), and linguistic dimensions. Unlike black-box models, fuzzy rules provide interpretable outputs that mirror educator reasoning, while genetic algorithms optimize variable weights for prediction accuracy and linguistic fairness. Grounded in self-regulated learning theory and sociocultural theory, the model incorporates multilingual code-switching competence, analyzing how English-Filipino-Cebuano patterns influence academic outcomes. Corpus analysis of 500 Cebu-based personal statements revealed that balanced trilingual students showed 27% higher academic resilience, while English-dominant profiles scored 19% lower on cultural adaptability measures. Testing with Psychology student profiles and deployment through an interactive dashboard demonstrated that students with strong behavioral indicators outperformed those with higher cognitive scores alone. Integrating multilingual competence factors improved prediction accuracy by 34% for linguistically diverse Central Visayas students compared to traditional cognitive-only models. The framework contributes to explainable AI by overcoming interpretability limitations of existing algorithms while incorporating cultural-linguistic factors ignored by conventional systems.

Keywords:

Code-Switching Competence; Multilingual Assessment; Explainable Artificial Intelligence; Educational Linguistics; Fuzzy-Genetic Algorithms

References

[1] Gyöngyvér, M., Ádám, K., 2024. Cognitive and non-cognitive predictors of academic success in higher education: a large-scale longitudinal study. Studies in Higher Education. DOI: http://dx.doi.org/10.1080/03075079.2023.2271513

[2] Christoph, M., 2022. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, 3rd ed. Available from: https://christophm.github.io/interpretable-ml-book/ (cited 20 May 2025).

[3] Scott, M.L., Su-In L., 2017. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS). 30. Available from: https://papers.nips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html

[4] Sachini, G., Mirka, S., 2025. Explainable AI in education: Techniques and qualitative assessment. Applied Sciences. 15(3), 1239. DOI: https://doi.org/10.3390/app15031239

[5] Shankar, S., Padmashri, N., Shanmugapriya, A., et al., 2025. IntelliFuzz: an advanced fuzzy logic framework for dynamic evaluation of student performance in open-ended learning tasks. International Journal of Computational and Experimental Science and Engineering. 11(1). DOI: https://doi.org/10.22399/ijcesen.911

[6] Anika, B., Hardik, T., Chitij, D., 2021. Evaluation of student performance using fuzzy logic. In Proceedings of the 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), Greater Noida, India, 17–18 December 2021; pp. 895–897. DOI: https://doi.org/10.1109/ICAC3N53548.2021.9725495

[7] Praveen, K., Gopal, S., 2023. Modelling student's performance evaluation using fuzzy logic techniques. International Journal of Creative Research Thoughts (IJCRT). 11(2), 973–981. Available from: https://ijcrt.org/papers/IJCRT2302368.pdf

[8] Lilik, A., Edy, S., Muhamad, Z., et al., 2021. Decision support system of student learning outcomes assessment on digital electronic subject using fuzzy logic. 2021 Fourth International Conference on Vocational Education and Electrical Engineering (ICVEE). 1–6. DOI: https://doi.org/10.1109/ICVEE54186.2021.9649735

[9] Ditdit, U., Deddy, K., 2021. Fuzzy based decision support model for deciding the students' academic performance. International Journal of Emerging Technology and Advanced Engineering. 11(10), 118–130. DOI: https://doi.org/10.46338/ijetae1021_15

[10] Zehra, Y., Baba, A.F., 2014. Evaluation of student performance in laboratory applications using fuzzy decision support system model. 2014 IEEE Global Engineering Education Conference (EDUCON). 1023–1027. DOI: https://doi.org/10.1109/EDUCON.2014.6826230

[11] Aruna, P., Lokhesh, R.J., Shajith, R.G.G., et al., 2023. Fuzzy logic expert system for analyzing student performance. 2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC). 885–890. DOI: https://doi.org/10.1109/I-SMAC58438.2023.10290708

[12] Vijiya, M., Arthi, M., 2019. Using fuzzy logic reasoning approach in fuzzy decision tree to evaluate students performance. International Journal of Applied Engineering Research. 14(2), 384–389. Available from: https://www.ripublication.com/ijaer19/ijaerv14n2_06.pdf

[13] Ditdit, N.U., 2023. An object oriented floating fuzzy decision model for evaluating the student performance. 2023 6th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI). 26–31. DOI: https://doi.org/10.1109/ISRITI60336.2023.10467360

[14] Gokhan, G., Tahir, C.A., Mehmet, T., et al., 2010. Evaluation of student performance in laboratory applications using fuzzy logic. Procedia Social and Behavioral Sciences. 2(2), 902–909. DOI: https://doi.org/10.1016/J.SBSPRO.2010.03.124

[15] Mohd, S.S., Amylia, A.T., Mohd, R.S., et al., 2025. Course recommendation system using fuzzy logic approach. Indonesian Journal of Electrical Engineering and Computer Science. 17(1), 365–371. DOI: https://doi.org/10.11591/ijeecs.v17.i1.pp365-371

[16] Paredes-Xochihua, M., Iván, R.S., Vianney, M., 2022. Algorithm for the selection of questions focused on education 4.0 using fuzzy logic. Journal Computer Technology. 6(16), 37–42. DOI: https://doi.org/10.35429/jct.2022.16.6.37.42

[17] Jingyang, L., 2024. The problems and countermeasures of private education management based on fuzzy logic system. Journal of Computational Methods in Science and Engineering. 24(1). DOI: https://doi.org/10.3233/JCM-237043

[18] Konstantin, K., Mansur, S., Rustam, B., 2023. Designing an educational intelligent system with natural language processing based on fuzzy logic. 2023 International Russian Smart Industry Conference (SmartIndustryCon). 690–694. DOI: https://doi.org/10.1109/SmartIndustryCon57312.2023.10110734

[19] Karthikeyan, A.A., Jagadeesha, R.D., Raha, S., 2023. Fuzzy logic systems with data classification—a cooperative approach for intelligent decision support. ICTACT Journal on Soft Computing. Available from: https://www.researchgate.net/profile/Shrinwantu-Raha/publication/375120593_FUZZY_LOGIC_SYSTEMS_WITH_DATA_CLASSIFICATION_-A_COOPERATIVE_APPROACH_FOR_INTELLIGENT_DECISION_SUPPORT/links/678e715582501639f5fcf794/FUZZY-LOGIC-SYSTEMS-WITH-DATA-CLASSIFICATION-A-COOPERATIVE-APPROACH-FOR-INTELLIGENT-DECISION-SUPPORT.pdf

[20] Hovhannisyan, L.A., Hakobyan, A.H., Antonyan, A.A., 2024. Integration of fuzzy logic at the system analysis stage in intelligent decision support systems. Proceedings of National Polytechnic University of Armenia. Information Technologies, Electronics, Radio Engineering. DOI: https://doi.org/10.53297/18293336-2024.2-65

[21] Meysam, S.K., Mohammad, S.A., 2012. Hybrid genetic algorithms for university course timetabling. International Journal of Computer Science Issues. 9(2). Available from: https://www.researchgate.net/publication/268423814_Hybrid_Genetic_Algorithms_for_University_Course_Timetabling

[22] Zhuohui, D., 2024. Fuzzy integrated optimization-based college and university music education teaching system. Journal of Electrical Systems. 20(5s). DOI: https://doi.org/10.52783/jes.1942

[23] Najeeb, U.J., Shabbar, N., Qambar, A., 2023. Using fuzzy logic for monitoring students academic performance in higher education. Engineering Proceedings. 46(1), 21. DOI: https://doi.org/10.3390/engproc2023046021

[24] Tomovic, M., Tomovic, C., Jovanovic, V., et al., 2025. Application of fuzzy logic for evaluation of student performance. In Proceedings of the 19th International Technology, Education and Development Conference, Valencia, Spain, 3–5 March 2025. Available from: https://library.iated.org/download/TOMOVIC2025APP

[25] Alibek, B., Bibigul, R., Altynbek, S., et al., 2025. Сomparative analysis of grading models using fuzzy logic to enhance fairness and consistency in student performance evaluation. Cogent Education. 12(1), 2481008. DOI: https://doi.org/10.1080/2331186X.2025.2481008

[26] Xiaoyan, H., 2023. Prediction of students' sports performance based on genetic neural network. Proceedings of the 2023 4th International Conference on Education, Knowledge and Information Management (ICEKIM 2023). Atlantis Press: Paris, France. pp. 1990–1994. DOI: https://doi.org/10.2991/978-94-6463-172-2_221

[27] Denny, K., Hendra, H., Muhammad, A., et al., 2023. Genetic algorithms for optimizing grouping of students classmates in engineering education. International Journal of Information and Education Technology. 13(12), 1907–1916. Available from: https://www.ijiet.org/show-195-2617-1.html

[28] Cindy, T., 2025. How is genetic algorithms used in education? Available from: https://www.byteplus.com/en/topic/503746 (cited 1 June 2025).

[29] Lumbardh, E., 2021. Personalized learning path generation based on genetic algorithms [Bachelor’s Thesis]. University for Business and Technology: Pristina, Kosovo. Available from: https://knowledgecenter.ubt-uni.net/etd/2135/

[30] Fuad, D., Nina, B., Drazena, G., 2020. Genetic algorithms as tool for development of balanced curriculum. Interdisciplinary Description of Complex Systems. 18(2-B), 175–193. Available from: https://www.scribd.com/document/481802404/indecs2020-pp175-193

[31] Harikumar, N., Zaid, A., Shweta, D., et al.,, 2024. Predicting academic performance of students using modified decision tree based genetic algorithm. 2024 Second International Conference on Data Science and Information System (ICDSIS). 1–5. DOI: https://doi.org/10.1109/ICDSIS61070.2024.10594426

[32] Salam, S.S., Hamza, T., Sana, A.A., et al., 2022. Enhanced binary genetic algorithm as a feature selection to predict student performance. Soft Computing. 26, 1811–1823. DOI: https://doi.org/10.1007/s00500-021-06424-7

[33] Rohani, Y., Torabi, Z., Kianian, S., 2020. A novel hybrid genetic algorithm to predict students' academic performance. Journal of Electrical and Computer Engineering Innovations (JECEI). 8(2), 219–232. DOI: https://doi.org/10.22061/JECEI.2020.7230.373

[34] Al, F., Halina, M.D., Samsuryadi, 2020. Genetic algorithm based feature selection with ensemble methods for student academic performance prediction. Journal of Physics: Conference Series. 1500, 012110. DOI: https://doi.org/10.1088/1742-6596/1500/1/012110

[35] Riyadh, M., Mirna, N., 2023. Genetic algorithm-based approach for predicting student academic success. 2023 24th International Arab Conference on Information Technology (ACIT). 1–5. DOI: http://dx.doi.org/10.1109/ACIT58888.2023.10453789

[36] Al, F., Halina, M.D., Samsuryadi, 2019. Genetic algorithm based feature selection for predicting student's academic performance. In: Saeed, F., Mohammed, F., Gazem, N. (eds.). Emerging Trends in Intelligent Computing and Informatics. IRICT 2019. Advances in Intelligent Systems and Computing, vol 1073. Springer: Cham, Switzerland. pp. 110–117. DOI: https://doi.org/10.1007/978-3-030-33582-3_11

[37] Sinta, R., Luthfia, R., Aprillia, 2024. Predicting graduation outcomes: decision tree model enhanced with genetic algorithm. Paradigma - Jurnal Komputer Dan Informatika. 26(1). DOI: https://doi.org/10.31294/p.v26i1.3165

[38] Stuti, S., Kaustubh, K., Arti, A., 2020. Integrating decision trees with metaheuristic search optimization algorithm for a student's performance prediction. 2020 IEEE Symposium Series on Computational Intelligence (SSCI). 655–661. DOI: https://doi.org/10.1109/SSCI47803.2020.9308241

[39] Chirag, B., 2025. Exploring the Power of AI in Creating Dynamic & Interactive Data Visualizations. Appinventiv: Noida, India. Available from: https://appinventiv.com/blog/ai-in-data-visualization/

[40] Doru-Anastasiu, P., 2025. An enhanced genetic algorithm for optimized educational assessment test generation through population variation. MDPI. 9(4), 98. DOI: https://doi.org/10.3390/bdcc9040098

[41] S. Ceschia, L., Gaspero, D., Schaerf, A., 2023. Educational timetabling: Problems, benchmarks, and state-of-the-art results. Journal of Scheduling. 26(6), 855–874. DOI: https://doi.org/10.1016/j.ejor.2022.07.011

[42] Kim, N.S., Efren, I.B., Jose, C.A.J., 2024. Optimizing course scheduling with genetic algorithms: A dynamic approach. SAR Journal. 7(4), 296–302. Available from: https://www.sarjournal.com/content/74/SARJournalDecember2024_296_302.pdf

[43] Xu, H., Dian, W., 2025. Gradual optimization of university course scheduling problem using genetic algorithm and dynamic programming. Algorithms. 18(3), 158. DOI: https://doi.org/10.3390/a18030158

[44] Lakshmi, T.M., Martin, A., Venkatesan, V.P., 2018. An analysis of students performance using genetic algorithm. Journal of Computer Science and Applications. 1(4), 75–79. Available from: https://pubs.sciepub.com/jcsa/1/4/3/jcsa-1-4-3.pdf

[45] Xiaoqian, L., 2025. Student achievement prediction and auxiliary improvement method based on fuzzy decision support system. Discover Artificial Intelligence. 5(63). DOI: https://doi.org/10.1007/s44163-025-00308-7

[46] Gallagher, M.A., Beck, J.S., Ramirez, E.M., et al., 2023. Supporting multilin­gual learners’ reading competence: a multiple case study of teachers’ instruction and student learning and motivation. Frontiers in Education. 8. DOI: https://doi.org/10.3389/feduc.2023.1085909

[47] Tatiane, R.B., André, A.L., Catia, M.d.S.M., et al., 2024. Applying a genetic algorithm to implement the fuzzyMACBETH method in decisionmaking processes. International Journal of Computational Intelligence Systems. 17(48) . DOI: https://doi.org/10.1007/s44196-024-00433-8

[48] Erdoğdu, A., Dayi, F., Yildiz, F., et al., 2025. Combining fuzzy logic and genetic algorithms to optimize cost, time and quality in modern agriculture. Sustainability. 17(7), 2829. DOI: https://doi.org/10.3390/su17072829

[49] Sapolnach, P., Charith, N., Steve, J., 2025. A practical guide for supporting formative assessment and feedback using generative AI. arXiv preprint. arXiv:2505.23405. DOI: https://doi.org/10.48550/arXiv.2505.23405

Downloads

How to Cite

B. Balijon, M. (2025). Explainable AI for Code-Switching Assessment in Philippine University Admissions. Forum for Linguistic Studies, 7(11), 1006–1026. https://doi.org/10.30564/fls.v7i11.11376

Issue

Vol. 7 , Iss. 11 (November 2025): In progress

Article Type

Article

License

Copyright © 2025 Meshel B. Balijon

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.