Chatbot Layanan Informasi Kelurahan Menggunakan Algoritma Naïve Bayes dan TF-IDF
DOI:
https://doi.org/10.29407/vvt07b85Abstract
Pelayanan publik di tingkat kelurahan sering terkendala oleh keterbatasan waktu operasional dan manajemen pengaduan warga yang masih manual. Penelitian ini bertujuan mengimplementasikan chatbot SIGRAK (Sistem Informasi Gerak Cepat) menggunakan metode Multinomial Naive Bayes dan pembobotan TF-IDF sebagai solusi digitalisasi layanan informasi di Kelurahan Kedondong. Metode pengembangan sistem meliputi tahap preprocessing teks, ekstraksi fitur, hingga integrasi pada framework Flask. Hasil penelitian menunjukkan bahwa model klasifikasi mencapai akurasi sebesar 96,24% pada pengujian data uji (213 data) dan 86,67% pada pengujian skenario interaksi nyata (120 data). Penurunan akurasi pada skenario nyata dipengaruhi oleh fenomena Out of Vocabulary dan overlapping features. Namun, penggunaan confidence threshold 30% berhasil meminimalisir kesalahan informasi.
Keywords:
chatbot, naive bayes, pelayanan publik, sigrak, tf-idf##plugins.themes.default.displayStats.downloads##
References
[1]. F. Agustian and A. Yuliana, “Aplikasi Chatbot Pelayanan Publik berbasis Website (Studi
Kasus Sekretariat DPRD Kota Cimahi),” J. Inform. dan Tek. Elektro Terap., vol. 12, no.
3S1, Oct. 2024, doi: 10.23960/jitet.v12i3S1.5202.
[2]. Sunarti, Ridwang, and M. A. M. Hayat, “Klasifikasi Pengaduan Pelayanan Fakultas Teknik
Universitas Muhammadiyah Makassar menggunakan Natural Language Processing,” Arus
J. Sains dan Teknol., vol. 2, no. 2, pp. 572–579, 2024, doi: 10.57250/ajst.v2i2.667.
[3]. R. C. Hutama, F. Fauziah, and R. T. Komalasari, “Aplikasi Chatbot Berbasis Teks
Menggunakan Algoritma Naive Bayes Classifier FAQ GrabAds,” STRING (Satuan
Tulisan Ris. dan Inov. Teknol., vol. 6, no. 1, p. 90, 2021, doi: 10.30998/string.v6i1.9919.
[4]. R. H. Ardiansyah and A. G. Sulaksono, “Layanan pelanggan berbasis Natural Language
Processing melalui chatbot pada aplikasi pesan,” J. Inf. Syst. Appl. Dev., vol. 1, no. 1, pp.
29–37, Mar. 2023, doi: 10.26905/jisad.v1i1.9858.
[5]. A. Muhidin, M. Danny, and E. Rilvani, “Algoritme Multinomial Naïve Bayes Pada
Aplikasi Chatbot Layanan Informasi Berbasis Teks,” Progresif J. Ilm. Komput., vol. 19,
no. 1, p. 71, 2023, doi: 10.35889/progresif.v19i1.1113.
[6]. S. Khoerunnisa, D. F. Shiddieq, and D. Nurhayati, “Penerapan Algoritma Naive Bayes
dengan Teknik TF-IDF dan Cross Validation untuk Analisis Sentimen Terhadap
Starlink,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 2, pp. 566–577,
2025, doi: 10.57152/malcom.v5i2.1852.
[7]. M. F. Yulianto, F. M. Hana, and A. Prihandono, “Penerapan Algoritma Naïve Bayes
dalam Analisis Sentimen terhadap Mobil Listrik,” Sainteks, vol. 22, no. 1, pp. 109–115,
2025, doi: 10.30595/sainteks.v22i1.26036.
[8]. Nurholis, Willy Prihartono, and Fathurrohman, “Web-Based Chatbot Development and
User Satisfaction Analysis Using the Naive Bayes Method Through Online
Questionnaires,” J. Artif. Intell. Eng. Appl., vol. 4, no. 2, pp. 1084–1090, 2025, doi:
10.59934/jaiea.v4i2.823.
[9]. R. Meinita and I. F. Anshori, “Perbandingan Algoritma Naïve Bayes dan Random Forest
untuk Klasifikasi Intent Chatbot Layanan Pelanggan,” J. Algoritm., vol. 5, no. 3, pp. 450–
462, 2025, doi: 10.35957/algoritme.v5i3.12639.
[10].L. Zhang, “Features extraction based on Naive Bayes algorithm and TF-IDF for news
classification,” PLoS One, vol. 20, no. 7 July, pp. 1–17, 2025, doi:
10.1371/journal.pone.0327347.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
