Design of an Automatic Help Desk Response Module Using Natural Language Processing
DOI:
https://doi.org/10.47709/brilliance.v5i1.6575Keywords:
Cosine Similarity, Enterprise System, Help Desk, Natural Language Processing, Text Classification, TF-IDFAbstract
Manual help desk systems in enterprise environments often suffer from delayed response times and repetitive queries, reducing service efficiency. This research aims to design an automated help desk response module by applying Natural Language Processing (NLP) techniques, specifically within the asset management context of an ERP system. The module uses Term Frequency-Inverse Document Frequency (TF-IDF) and cosine similarity to classify incoming queries and retrieve relevant answers from a predefined knowledge base. Python, Django, PostgreSQL, Scikit-learn, and NLTK were used to implement the module. Testing was conducted using 50 sample queries, resulting in an accuracy of 90% based on confusion matrix evaluation. The system successfully retrieves appropriate responses for most frequent user issues. This design is expected to support organizations in streamlining their help desk operations and improving response time and consistency. Future developments may involve semantic matching and machine learning-based improvements to enhance understanding of unstructured queries.
References
Adiwinata, C., Marbun, R., & Rahayu, P. (2024). IMPLEMENTATION OF HELPDESK CHATBOT APPLICATION FOR INFORMATION SYSTEM SERVICES IN HIGHER EDUCATION. JURNAL INSTEK?: INFORMATIKA SAINS DAN TEKNOLOGI, 9.
Al Rasyid, R., Handayani, D., & Ningsih, U. (2024). Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata. Jurnal Teknologi Informasi Dan Komunikasi), 8(1). https://doi.org/10.35870/jti
Bali?, A., Turulja, L., Kuloglija, E., & Peji?-Bach, M. (2022). ERP Quality and the Organizational Performance: Technical Characteristics vs. Information and Service. Information (Switzerland), 13(10). https://doi.org/10.3390/info13100474
Fadillah Effendi, H., Assegaff, S., Sistem Informasi, M., Dinamika Bangsa, U., & Jl Jend Sudirman Thehok-Jambi, J. (2022). IT Helpdesk Ticketing System Berbasis Web Pada Bagian ERP (Enterprise Resource Planning) PT Perkebunan Nusantara VI. Journal Manajemen Sistem Informasi Universitas Dinamika Bangsa, 7(3).
Hayati, R., Buaton, R., Ramadani, S., & Kaputama, S. (2024). Implementation of Chatbot Artificial Intelligence in a Company Website to Improve Customer Service Automatically Using the TF-IDF Method. 4(1). Retrieved from https://ioinformatic.org/
Juni Permana, A. H. J. P., & Agung Toto Wibowo. (2023). Movie Recommendation System Based on Synopsis Using Content-Based Filtering with TF-IDF and Cosine Similarity. International Journal on Information and Communication Technology (IJoICT), 9(2), 1–14. https://doi.org/10.21108/ijoict.v9i2.747
Nugroho, A. F. J., & Fianty, M. I. (2023). Streamlining IT Help Desk and Incident Management: Harnessing the Power of the ITIL Framework for Enhanced Efficiency in IT Services. Journal of Information Systems and Informatics, 5(2), 683–695. https://doi.org/10.51519/journalisi.v5i2.496
Olujimi, P. A., & Ade-Ibijola, A. (2023). NLP techniques for automating responses to customer queries: a systematic review. Discover Artificial Intelligence, 20(3). https://doi.org/10.1007/s44163-023-00065-5
Omkar Kunde, Omkar Gaikwad, Prathamesh Kelgandre, Rohan Damodhar, & Prof. Mrs. M. M. Swami. (2022). The Movie Recommendation System using Content Based Filtering with TF-IDF¬¬-Vectorization and Levenshtein Distance. International Journal of Advanced Research in Science, Communication and Technology, (2), 257–263. https://doi.org/10.48175/ijarsct-3648
Prasetya, M. R. A., & Priyatno, A. M. (2022). Dice Similarity and TF-IDF for New Student Admissions Chatbot. RIGGS: Journal of Artificial Intelligence and Digital Business, 1(1), 13–18. https://doi.org/10.31004/riggs.v1i1.5
Rendy Usmany. (2022). PENGEMBANGAN CHATBOT PENGADUAN DAN TROUBLESHOOTING TEKNOLOGI INFORMASI DENGAN PENDEKATAN NLP (STUDI KASUS POLITEKNIK NEGERI AMBON). JURNAL SIMETRIK, 12(2).
Rinaldi, A., Hiryanto, L., & Mawardi Christianti, V. (2023). Jurnal Ilmu Komputer dan Sistem Informasi PENERAPAN TF-IDF DAN COSINE SIMILARITY PADA QUESTION AND ANSWERING SYSTEM TERKAIT INFORMASI KONSOL DAN GAME PLAYSTATION. Jurnal Ilmu Komputer Dan Sistem Informasi.
Setiawan, G. H., Made, I., & Adnyana, B. (2023). Improving Helpdesk Chatbot Performance with Term Frequency-Inverse Document Frequency (TF-IDF) and Cosine Similarity Models. Journal of Applied Informatics and Computing (JAIC), 7(2), 252–157. Retrieved from http://jurnal.polibatam.ac.id/index.php/JAIC
Setiawan, M. D., & Eliyani, E. (2022). Pengembangan Aplikasi Helpdesk Ticketing System Dengan Algoritma Multinomial Naïve Bayes Classifier. Jurnal Ilmiah FIFO, 14(2), 113. https://doi.org/10.22441/fifo.2022.v14i2.001
Tjahjanto, T., Arista, A., & Ermatita, E. (2022). Information System for State-owned inventories Management at the Faculty of Computer Science. Sinkron, 7(4), 2182–2192. https://doi.org/10.33395/sinkron.v7i4.11678
Wibowo, A., & Hariyanto. (2023). Comparison of Naive Bayes Method with Support Vector Machine in Helpdesk Ticket Classification. Journal of Applied Informatics and Computing (JAIC), 7(2), 165–171. Retrieved from http://jurnal.polibatam.ac.id/index.php/JAIC
Yuhandri, Sovia, R., Syaiffullah, A., Yenila, F., & Permana, R. (2023). Penerapan Natural Language Processing Pada Sistem Chatbot Sebagai Helpdesk Obyek Wisata Menggunakan Metode Naïve Bayes. Jurnal Infortech, 5(2). Retrieved from http://ejournal.bsi.ac.id/ejurnal/index.php/infortech210
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Tri Mur Fridayanto, Ari Purno Wahyu Wibowo
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
info@itscience.org, web: 
