Development of a Web-Based Resume-Job Matching System Using Transformer Embeddings and Weighted Jaccard Similarity at Systems Plus College Foundation, Inc.
Keywords:
Visual Optical Character Recognition, Transformer-based embeddings, Weighted Jaccard Similarity, Semantic alignment, Hybrid Transformer–Jaccard approach, V-Model methodology, ISO/IEC 25010 standardsAbstract
Recruitment workflows often suffer from operational bottlenecks due to manual resume screening and rigid keyword matching, which fail to capture contextual qualifications and encounter extraction errors from diverse document layouts. To address these challenges, this study proposes the development of a web-based resume-job matching system for Systems Plus College Foundation, Inc. utilizing layout-aware visual Optical Character Recognition (OCR), Transformer-based embeddings, and Weighted Jaccard Similarity. The system integrates a visual OCR engine to extract structured text from complex, multi-column resume layouts and generates high-dimensional vector representations to measure contextual semantic alignment against job descriptions. It also utilizes Weighted Jaccard Similarity to evaluate explicit skill overlap based on term criticality, producing a calibrated candidate compatibility score. The proposed hybrid Transformer–Jaccard approach will be benchmarked against conventional keyword-based screening across four primary performance measures: layout-parsing accuracy, semantic extraction precision, runtime processing efficiency, and false rejection rates. Following a Developmental Research Design with a Quantitative Approach implemented through the V-Model methodology, the system offloads heavy processing tasks to asynchronous background queues while delivering ranked candidate analytics to a web dashboard. The study will also evaluate user acceptance based on ISO/IEC 25010 standards to confirm functional suitability and usability. The system is expected to improve initial screening accuracy over traditional keyword methods and provide human resource personnel with a transparent, data-driven decision-support tool for optimizing institutional hiring workflows.
References
Abhishek, K. L., Niranjanamurthy, M., Aric, S., Ansarullah, S. I., Sinha, A., Tejani, G., & Shah, M. A. (2025). Developing an intelligent resume screening tool with AI-driven analysis and recommendation features. Applied AI Letters, 6(2), e116. https://doi.org/10.1002/ail2.116
Agngarayngay, C. D., Latifi, S. I., Marco, F. J. P., Tan, C. E., & Villamor-Evangelista, M. G. (2026). AI integration in screening and selection: The impact of perception of fairness, trust, and usability in the acceptability of HR employees in Metro Manila. International Journal of Business and Social Science Research, 7(3). https://doi.org/10.47742/ijbssr.v7n3p2
Alsaif, S. A., Hidri, M. S., Ferjani, I., Eleraky, H. A., & Hidri, A. (2022). NLP-based bi-directional recommendation system: Towards recommending jobs to job seekers and resumes to recruiters. Big Data and Cognitive Computing, 6(4), Article 147. https://doi.org/10.3390/bdcc6040147
Appalaraju, S., Jasani, B., Kota, B. U., Xie, Y., & Manmatha, R. (2021). DocFormer: End-to-end transformer for document understanding. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 993–1003). IEEE. https://openaccess.thecvf.com/content/ICCV2021/html/Appalaraju_DocFormer_End-to-End_Transformer_for_Document_Understanding_ICCV_2021_paper.html
Bullhorn. (2022, September 28). Poor hiring processes cause 75% of Gen Z to abandon promising job applications. https://www.bullhorn.com/news-and-press/press-releases/gen-z-talent-survey/
Çelik Ertuğrul, D., & Bitirim, S. (2025). Job recommender systems: A systematic literature review, applications, open issues, and challenges. Journal of Big Data, 12, Article 140. https://doi.org/10.1186/s40537-025-01173-y
Chanda, P., Sri, T. B., Tejasree, C., Vardhan, N. M., & Rohith, M. (2026). Resume screening system with semantic search, bias-mitigation, and explainability. International Journal of Scientific Development and Research, 11(2). https://ijsdr.org/papers/IJSDR2602024.pdf
Dadaboyev, S. M. U., Abdullayeva, J., Abbosova, N., & Suleymenova, A. (2025). Role of artificial intelligence in employee recruitment: Systematic review and future research directions. Discover Global Society, 3, Article 99. https://doi.org/10.1007/s44282-025-00246-w
González-Morales, A., Martín-López, M. M., & Góngora-Larequi, F. (2026). A systematic review and descriptive analysis of artificial intelligence applied to recruitment and personnel selection in the present and possible future. Discover Artificial Intelligence, 6, Article 762. https://doi.org/10.1007/s44163-026-01488-6
Huang, Y., Lv, T., Cui, L., Lu, Y., & Wei, F. (2022). LayoutLMv3: Pre-training for document AI with unified text and image masking. In Proceedings of the 30th ACM International Conference on Multimedia (pp. 4083–4091). Association for Computing Machinery. https://doi.org/10.1145/3503161.3548112
Hunkenschroer, A. L., & Kriebitz, A. (2023). Is AI recruiting (un)ethical? A human rights perspective on the use of AI for hiring. AI and Ethics, 3(1), 199–213. https://doi.org/10.1007/s43681-022-00166-4
Hunkenschroer, A. L., & Luetge, C. (2022). Ethics of AI-enabled recruiting and selection: A review and research agenda. Journal of Business Ethics, 178(4), 977–1007. https://doi.org/10.1007/s10551-022-05049-6
Jagadeesh, A., Ravi Shankar, C., Narayanaswamy Patel, S., Levantesi, M., Semeraro, G., & De Luca, E. W. (2025). AI-driven resume analysis and enhancement using semantic modeling and large language feedback loops. In Proceedings of the Eleventh Italian Conference on Computational Linguistics (pp. 526–538). CEUR Workshop Proceedings. https://aclanthology.org/2025.clicit-1.51/
Rosenberger, J., Wolfrum, L., Weinzierl, S., Kraus, M., & Zschech, P. (2025). CareerBERT: Matching resumes to ESCO jobs in a shared embedding space for generic job recommendations. Expert Systems with Applications, 275, Article 127043. https://doi.org/10.1016/j.eswa.2025.127043
United Nations Department of Economic and Social Affairs. (n.d.-a). Goal 8: Decent work and economic growth. United Nations. https://sdgs.un.org/goals/goal8
United Nations Department of Economic and Social Affairs. (n.d.-b). Goal 9: Industry, innovation and infrastructure. United Nations. https://sdgs.un.org/goals/goal9
Vedija, M. L., & Martir, E. M. (2026). Utilization of artificial intelligence in human resource management recruitment: Its opportunities and challenges. Iconic Research and Engineering Journals, 9(11), 4042–4062. https://doi.org/10.64388/IREV9I11-1718388
Werner, M., & Laber, E. (2024). Extracting section structure from resumes in Brazilian Portuguese. Expert Systems with Applications, 242, Article 122495. https://doi.org/10.1016/j.eswa.2023.122495
Yan, Y. (2026). Transformer-based semantic embedding model for resume-job matching in intelligent talent screening. Artificial Intelligence and Digital Technology, 3(1), 82–91. https://doi.org/10.70088/mvanpe51
Zhang, P. (2024). Application of artificial intelligence (AI) in recruitment and selection: The case of Company A and Company B. Journal of Business and Management Studies, 6(3). https://doi.org/10.32996/jbms.2024.6.3.18
Zhang, Y., Qiao, M., Peng, Z., & Deng, D. (2026). Near-duplicate text alignment under weighted Jaccard similarity. Proceedings of the VLDB Endowment, 19(7), 1600–1613. https://doi.org/10.14778/3801059.3801072
Zhu, F., Yu, J., Chen, Z., Zhou, Y., Ji, J., Yang, Z., Zhang, Y., Hu, H., & Liu, Z. (2025). Layout-aware parsing meets efficient LLMs: A unified, scalable framework for resume information extraction and evaluation (arXiv:2510.09722). arXiv. https://arxiv.org/abs/2510.09722
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Kenneth C. Carillo, Kurt Russel Cano, Benedict C. Garcia, Clarence Paul Q. Lazaro (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
