Integrasi Rule-Based dan TF-IDF Cosine Similarity untuk Klasifikasi Prioritas dan Delegasi Tugas Berbasis SOP

Muhammad Fajar Alin Faza; Elkaf Rahmawan Pramudya

doi:10.55681/armada.v4i10.4523

Authors

Muhammad Fajar Alin Faza Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Universitas Dian Nuswantoro, Semarang, Indonesia
Elkaf Rahmawan Pramudya Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Universitas Dian Nuswantoro, Semarang, Indonesia

DOI:

https://doi.org/10.55681/armada.v4i10.4523

Keywords:

Cosine Similarity, Delegasi Tugas, Hybrid Cascading, Klasifikasi Teks, Standar Operasional Prosedur

Abstract

Ketidaktepatan klasifikasi keluhan dan delegasi tugas manual pada organisasi multi-divisi menyebabkan penumpukan tiket, kesalahan perutean, dan keterlambatan eskalasi insiden kritis. Sistem berbasis aturan menjamin kepatuhan terhadap Standar Operasional Prosedur (SOP), tetapi rentan terhadap variasi bahasa informal, sedangkan TF-IDF Cosine Similarity lebih adaptif secara leksikal namun tidak menjamin kepatuhan deterministik. Penelitian ini mengusulkan arsitektur Hybrid Cascading dengan confidence gating, yang mengintegrasikan Knowledge Base SOP Telkom sebagai penyaring deterministik dan TF-IDF Cosine Similarity sebagai mekanisme fallback. Evaluasi menggunakan 538 teks komplain tanpa label awal yang dipetakan melalui distant supervision SOP serta 96 data uji berlabel, termasuk 40% variasi bahasa informal, slang, dan ungkapan ambigu. Hasil menunjukkan akurasi klasifikasi kategori sebesar 83,33%, akurasi delegasi divisi 90,62%, dan Macro F1-Score 83,69%, melampaui kedua model dasar. Sebanyak 59,38% kasus diselesaikan melalui aturan SOP, sedangkan 40,62% ditangani melalui fallback TF-IDF. Temuan ini menunjukkan bahwa integrasi sekuensial aturan dan metode statistik berpotensi meningkatkan akurasi delegasi serta menjaga kepatuhan terhadap regulasi operasional.

Downloads

Download data is not yet available.

References

Adli, H. R., Megasari, R., & U. P. Indonesia. (2023). Implementation of inverse document frequency (TF-IDF) and cosine similarity terms in determining research reviewers for Indonesian Education University lecturers. Journal of Computing and Society, 4(2), 73–82.

Allam, H., Makubvure, L., Gyamfi, B., Graham, K. N., & Akinwolere, K. (2025). Text classification: How machine learning is revolutionizing text categorization. Information, 16(2), 1–47. https://doi.org/10.3390/info16020130

Arifman, F., Mantoro, T., & Handayani, D. O. D. (2026). A hybrid machine learning approach for classifying Indonesian cybercrime discourse using a localized threat taxonomy. Information, 17(3), 1–25. https://doi.org/10.3390/info17030301

Aththanayake, S., Mallikarachchi, C., Wickramasinghe, J., Kugarajah, S., Meedeniya, D., & Pradhan, B. (2026). ResQConnect: An AI-powered multi-agentic platform for human-centered and resilient disaster response. Sustainability, 18(2), 1–48. https://doi.org/10.3390/su18021014

Arowosegbe, A., & Oyelade, T. (2023). Application of natural language processing (NLP) in detecting and preventing suicide ideation: A systematic review. International Journal of Environmental Research and Public Health, 20(2), 1–23. https://doi.org/10.3390/ijerph20021514

Bhattacharya, D., Krishnamurthy, P., & Shyam Sundar, K. R. (2023). Customer service ticket classification using machine learning and natural language processing. International Journal of Computer Applications, 185(6), 1–8. https://doi.org/10.5120/ijca2023922882

Ding, Y., Han, S. C., Lee, J., & Hovy, E. (2026). Deep learning-based visually rich document content understanding: A survey. Artificial Intelligence Review, 59(4), 1–63. https://doi.org/10.1007/s10462-025-11477-3

Ehrgott, M., Köksalan, M., Kadziński, M., & Deb, K. (2026). Fifty years of multi-objective optimization and decision-making: From mathematical programming to evolutionary computation. European Journal of Operational Research, 330(1), 1–25. https://doi.org/10.1016/j.ejor.2025.06.012

Fu, S., et al. (2023). Recommended practices and ethical considerations for natural language processing-assisted observational research: A scoping review. Clinical and Translational Science, 16(3), 398–411. https://doi.org/10.1111/cts.13463

Golec, J., & Hachaj, T. (2025). Ten natural language processing tasks with generative artificial intelligence. Applied Sciences, 15(16), 1–30. https://doi.org/10.3390/app15169057

González, T. R., Rocha, M. A., Baltazar, R., Casillas, M. Á., & del Valle, J. (2022). Voice control system through NLP (natural language processing) as an interactive model for scalable ERP platforms in Industry 4.0. In Smart innovation, systems and technologies (Vol. 306, pp. 207–217). Springer. https://doi.org/10.1007/978-981-19-3359-2_18

Greco, C. M., & Tagarelli, A. (2024). Bringing order into the realm of transformer-based language models for artificial intelligence and law. Artificial Intelligence and Law, 32(4), 883–924. https://doi.org/10.1007/s10506-023-09374-7

Harris, S., Hadi, H. J., Ahmad, N., & Alshara, M. A. (2024). Fake news detection revisited: An extensive review of theoretical frameworks, dataset assessments, model constraints, and forward-looking research agendas. Technologies, 12(11), 1–63. https://doi.org/10.3390/technologies12110222

Hendry, H., Tukino, T., Sediyono, E., Fauzi, A., & Huda, B. (2025). HyEWCos: A comparative study of hybrid embedding and weighting techniques for text similarity in short subjective educational text. Information, 16(11), 1–28. https://doi.org/10.3390/info16110995

Huynh, L., & McNamara, D. S. (2025). Natural language processing as a scalable method for evaluating educational text personalization by LLMs. Applied Sciences, 15(22), 1–26. https://doi.org/10.3390/app152212128

Jiang, S. (2025). Big data sharing: A comprehensive survey. Data, 10(11), 1–35. https://doi.org/10.3390/data10110182

Li, J., Sun, M., & Wu, Z. (2022). A survey on deep learning for named entity recognition. IEEE Transactions on Knowledge and Data Engineering, 34(1), 50–70. https://doi.org/10.1109/TKDE.2020.2981314

Okaka, R. A., Mwangi, W., & Okeyo, G. (2016). A hybrid approach for personalized recommender system using weighted TF-IDF on RSS contents. International Journal of Computer Applications Technology and Research, 5(12), 764–774. https://doi.org/10.7753/ijcatr0512.1006

Pothuri, V. R. V. (2025). Natural language processing in conversational AI. International Research Journal of Modern Engineering Technology and Science, (9), 436–440. https://doi.org/10.4018/979-8-3373-4217-7.ch011

Pratibha, Kaur, A., Khurana, M., & Damaševičius, R. (2024). Multimodal Hinglish tweet dataset for deep pragmatic analysis. Data, 9(2), 1–19. https://doi.org/10.3390/data9020038

Savvadelli, E., Kiouvrekis, Y., & Kokkinaki, A. (2026). A literature review on rule-based systems as decision support systems. In IFIP advances in information and communication technology (Vol. 761, pp. 376–388). Springer. https://doi.org/10.1007/978-3-032-02504-3_26

Soga, L. R., Bolade-Ogunfodun, Y., Mariani, M., Nasr, R., & Laker, B. (2022). Unmasking the other face of flexible working practices: A systematic literature review. Journal of Business Research, 142, 648–662. https://doi.org/10.1016/j.jbusres.2022.01.024

Umer, M., Ashraf, I., Mehmood, A., Ullah, S., & Choi, G. S. (2021). Predicting numeric ratings for Google Apps using text features and regression algorithms. ETRI Journal, 43(1), 95–107. https://doi.org/10.4218/etrij.2019-0299

Vuković, D., Žunac, A. G., & Jurič, B. (2023). Customer experience as an important factor in evaluating telecommunications services. International Journal for Quality Research, 17(2), 427–440. https://doi.org/10.24874/IJQR17.02-08

Wang, J., & Shalaby, A. (2026). ELSSA: Explainable large language model-based decision support for public transit incident management. Transportation Research Part C: Emerging Technologies, 193, Article 105923. https://doi.org/10.1016/j.trc.2026.105923

Wang, Y., Liu, Y., & Sun, H. (2023). A hybrid text classification approach using rule-based and statistical methods for customer complaint routing. Expert Systems with Applications, 213, Article 119086. https://doi.org/10.1016/j.eswa.2022.119086

Widianto, A., Pebriyanto, E., & Fitriyanti, M. (2025). Document similarity using term frequency-inverse document frequency representation and cosine similarity. Data Science and Information Technology Data Analysis, 4(2), 149–153.

Zhou, J., Ye, Z., Zhang, S., Geng, Z., Han, N., & Yang, T. (2024). Investigating response behavior through TF-IDF and Word2vec text analysis: A case study of PISA 2012 problem-solving process data. Heliyon, 10(16), Article e35945. https://doi.org/10.1016/j.heliyon.2024.e35945