Pengembangan Chatbot Untuk Layanan Satuan Penjaminan Mutu (SPM) Menggunakan Bert (Bidirectional Encoder Representations From Transformers)
Abstract
Abstrak — Kendala Satuan Penjaminan Mutu (SPM) dalam penyampaian informasi yang kurang efisien, menyebabkan pelayanan Satuan Penjaminan Mutu (SPM) kurang responsif. Sehingga dibutuhkannya chatbot yang merespon secara cepat dan tepat. Penelitian ini berfokus pada pengembangan chatbot berbasis deep learning dengan arsitektur BERT untuk layanan Satuan Penjaminan Mutu (SPM) sebagai platform pembantu. Tujuannya adalah untuk memaksimalkan pencarian data dan penyampaian informasi yang efisien kepada pengguna. Metodologi yang digunakan meliputi pengumpulan data mentah dari SPM (Penelitian, Pengabdian, Prestasi, Mahasiswa, dan Dosen dari 2019-2024), pra-pengolahan data (tokenisasi, padding, label encoding), dan pengembangan model BERT yang diintegrasikan dengan platform Telegram. Evaluasi model melalui 15 percobaan menunjukkan performa optimal pada konfigurasi tertentu dengan akurasi tinggi dan tingkat kesalahan rendah, terbukti dari F1-score kelas positif mencapai 0.9831. Meskipun terdapat sedikit ketidaksesuaian pada satu skenario pengujian black-box dan adanya cold start pada respons awal chatbot, hasil kuesioner pengguna secara keseluruhan menunjukkan kepuasan tinggi terhadap kemudahan penggunaan dan kecepatan respons. Implementasi chatbot ini diharapkan meningkatkan efisiensi layanan SPM, meskipun perlu penambahan variasi data pelatihan dan deployment ke server untuk optimalisasi lebih lanjut.
Kata kunci— Chatbot, Deep Learning, BERT (Bidirectional Encoder Representations from Transformers), Natural Language Processing, Blackbox Testing, Telegram.
Downloads
References
[1] J. Byun, B. Kim, K. A. Cha, and E. Lee, “Design and Implementation of an Interactive Question-Answering System with Retrieval-Augmented Generation for Personalized Databases,” Applied Sciences (Switzerland), vol. 14, no. 17, 2024, doi: 10.3390/app14177995.
[2] C. V. Misischia, F. Poecze, and C. Strauss, “Chatbots in customer service: Their relevance and impact on service quality,” Procedia Comput Sci, vol. 201, no. C, pp. 421–428, 2022, doi: 10.1016/j.procs.2022.03.055.
[3] M. P. Naresh, S. Venkataramana, N. Pavan, A. R. Mohammed, M. Tharun, and N. Chanti, “Implementing a Flask-based Chatbot for College Enquiries using Spacy and TensorFlow,” vol. 14, no. 05, pp. 77–82, 2023.
[4] S. Pokhrel, “A Systematic Review of Chatbot Model and chatbot technologies,” Αγαη, vol. 15, no. 1, pp. 37–48, 2024, [Online]. Available: https://www.ieeesem.com/researchpaper/A_Systematic_Literature_Review_and_Existing_Challenges_of_Chatbot_Models.pdf
[5] S. Sharma and P. Chaudhary, “Machine learning and deep learning,” Quantum Computing and Artificial Intelligence: Training Machine and Deep Learning Algorithms on Quantum Computers, pp. 71–84, 2023, doi: 10.1515/9783110791402-004.
[6] I. H. Sarker, “Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions,” SN Comput Sci, vol. 2, no. 6, pp. 1–20, 2021, doi: 10.1007/s42979-021-00815-1.
[7] D. Dharrao and S. Gite, “TherapyBot: a chatbot for mental well-being using transformers,” International Journal of Advances in Applied Sciences, vol. 13, no. 1, pp. 1–12, 2024, doi: 10.11591/ijaas.v13.i1.pp1-12.
[8] Q. Zhou et al., “GastroBot: a Chinese gastrointestinal disease chatbot based on the retrieval-augmented generation,” Front Med (Lausanne), vol. 11, no. May, 2024, doi: 10.3389/fmed.2024.1392555.
[9] T. A. Zuraiyah, D. K. Utami, and D. Herlambang, “Implementasi Chatbot Pada Pendaftaran Mahasiswa Baru Menggunakan Recurrent Neural Network,” Jurnal Ilmiah Teknologi dan Rekayasa, vol. 24, no. 2, pp. 91–101, 2019, doi: 10.35760/tr.2019.v24i2.2388.
[10] A. Babu and S. B. Boddu, “BERT-Based Medical Chatbot: Enhancing Healthcare Communication through Natural Language Understanding,” Exploratory Research in Clinical and Social Pharmacy, vol. 13, no. January, p. 100419, 2024, doi: 10.1016/j.rcsop.2024.100419.
[11] E. Adamopoulou and L. Moussiades, An Overview of Chatbot Technology, vol. 584 IFIP, no. June. Springer International Publishing, 2020. doi: 10.1007/978-3-030-49186-4_31.
[12] S. Ayanouz, B. A. Abdelhakim, and M. Benhmed, “A Smart Chatbot Architecture based NLP and Machine Learning for Health Care Assistance,” ACM International Conference Proceeding Series, no. April, 2020, doi: 10.1145/3386723.3387897.
[13] C. S. Patil, “NLP Assisted Text Annotation,” Interantional Journal of Scientific Research in Engineering and Management, vol. 06, no. 06, pp. 1–10, 2022, doi: 10.55041/ijsrem14651.
[14] J. A. Alzubi, R. Jain, A. Singh, P. Parwekar, and M. Gupta, “COBERT: COVID-19 Question Answering System Using BERT,” Arab J Sci Eng, vol. 48, no. 8, pp. 11003–11013, 2023, doi: 10.1007/s13369-021-05810-5.
[15] M. V. Koroteev, “BERT: A Review of Applications in Natural Language Processing and Understanding,” 2021, [Online]. Available: http://arxiv.org/abs/2103.11943
[16] Supriyono, “Software Testing with the approach of Blackbox Testing on the Academic Information System,” International Journal of Information System & Technology, vol. 3, no. 36, pp. 227–235, 2020.
[17] J. Shadiq, A. Safei, and R. W. R. Loly, “Pengujian Aplikasi Peminjaman Kendaraan Operasional Kantor Menggunakan BlackBox Testing,” INFORMATION MANAGEMENT FOR EDUCATORS AND PROFESSIONALS : Journal of Information Management, vol. 5, no. 2, p. 97, 2021, doi: 10.51211/imbi.v5i2.1561.
