Implementation of the Naïve Bayes Algorithm for Sentiment Analysis of Portos Coffee Shop Customer Reviews Using a Natural Language Processing (NLP) Approach

Yakub Mas Arbi Sitompul; Marah Dolly Nst

doi:10.59890/ijetr.v4i3.15

Authors

Yakub Mas Arbi Sitompul Universitas Muhammadiyah Sumatera Utara
Marah Dolly Nst Universitas Muhammadiyah Sumatera Utara

DOI:

https://doi.org/10.59890/ijetr.v4i3.15

Keywords:

Sentiment analysis, Multinomial Naïve Bayes, Natural language processing, TF-IDF, Coffee shop

Abstract

This study implements the Multinomial Naïve Bayes (MNB) algorithm with a Natural Language Processing (NLP) approach to classify customer sentiment toward Portos Coffee Shop and builds a web-based monitoring system. A total of 586 reviews from Google Maps (525) and Instagram (61), collected in 2026, were preprocessed with Sastrawi stemming, weighted using TF-IDF, and labeled by a hybrid rating–InSet lexicon method. Hold-out testing (80:20) achieved 87.29% accuracy and a 90.20% F1-score, while 5-fold cross-validation averaged 90.79% accuracy. Positive sentiment accounted for 62.12% of reviews. The model was deployed using FastAPI, Next.js, PostgreSQL, and Docker, and passed all unit and black-box tests.

References

Adi Pranata, I. A., et al. (2018). Rancang bangun RESTful API sistem informasi geografis [Design and development of a RESTful API for a geographic information system]. Jurnal Teknologi Informasi dan Komputer, 4(1), 45–52.

Apriliani, D., et al. (2023). Analisis sentimen masyarakat terhadap vaksinasi Covid-19 menggunakan algoritma K-Nearest Neighbors [Sentiment analysis of public opinion on Covid-19 vaccination using the K-Nearest Neighbors algorithm]. Jurnal Informatika dan Rekayasa Perangkat Lunak, 5(1), 12–20.

Aryandi, F., et al. (2023). Analisis sentimen ulasan pelanggan pada Google Maps menggunakan text mining [Sentiment analysis of customer reviews on Google Maps using text mining]. Jurnal Sains dan Teknologi Informasi, 8(2), 101–109.

Asih, N. L., et al. (2023). Komparasi algoritma Decision Tree dan Naïve Bayes untuk mengukur kepuasan pelanggan Starbucks [Comparison of the Decision Tree and Naïve Bayes algorithms for measuring Starbucks customer satisfaction]. Jurnal Sistem Informasi dan Data Science, 2(1), 33–41.

Azhari, M., et al. (2021). Evaluasi kinerja algoritma klasifikasi teks dalam pemrosesan bahasa alami [Performance evaluation of text classification algorithms in natural language processing]. Jurnal Riset Komputer, 8(3), 142–150.

Darwis, D., et al. (2021). Penerapan algoritma Naïve Bayes dalam analisis sentimen opini publik [Application of the Naïve Bayes algorithm in public opinion sentiment analysis]. Jurnal Teknoinfo, 15(1), 29–35.

Dewi, S., et al. (2023). Pengujian black box pada sistem informasi manajemen berbasis web [Black-box testing of a web-based management information system]. Jurnal Rekayasa Perangkat Lunak, 4(2), 88–95.

Handayanto, A., et al. (2021). Analisis sentimen Google Review menggunakan Naive Bayes Classifier [Sentiment analysis of Google Reviews using the Naive Bayes Classifier]. Jurnal Informatika Medika, 3(2), 67–75.

Hasanah, U., & Sari, Y. (2024). Klasifikasi sentimen pengguna aplikasi Maxim menggunakan Naïve Bayes Classifier [Sentiment classification of Maxim application users using the Naïve Bayes Classifier]. Jurnal Media Informatika Budidarma, 8(1), 205–214.

Hidayatullah, A., et al. (2022). Analisis sentimen komentar Instagram produk Eiger menggunakan Naïve Bayes Classifier [Sentiment analysis of Instagram comments on Eiger products using the Naïve Bayes Classifier]. Jurnal Teknologi dan Sistem Komputer, 10(2), 115–123.

Hilma, F., et al. (2023). Perbandingan Support Vector Machine dan Naïve Bayes dalam klasifikasi cyberbullying [Comparison of Support Vector Machine and Naïve Bayes in cyberbullying classification]. Jurnal Edukasi dan Penelitian Informatika, 9(1), 50–58.

Irvandi, M., et al. (2023). Analisis sentimen wisata halal Pulau Lombok menggunakan Naïve Bayes dan wordcloud [Sentiment analysis of halal tourism in Lombok Island using Naïve Bayes and wordcloud]. Jurnal Ilmiah Komputasi, 22(3), 310–318.

Koto, F., & Rahmaningtyas, G. Y. (2017). InSet lexicon: Evaluation of a wordlist for Indonesian sentiment analysis. In Proceedings of the 1st International Conference on Asian Language Processing (IALP) (pp. 1–6).

Lathkar, M. (2023). Python API development with FastAPI. Apress.

Lestandy, M., et al. (2021). Analisis sentimen citra merek menggunakan algoritma Naïve Bayes [Sentiment analysis of brand image using the Naïve Bayes algorithm]. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 5(4), 720–727.

Liu, B. (2012). Sentiment analysis and opinion mining. Morgan & Claypool Publishers.

Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to information retrieval. Cambridge University Press.

Nugroho, A., & Winarko, E. (2013). Sistem manajemen basis data relasional [Relational database management systems]. Andi Offset.

Nurian, R., & Sari, Y. (2023). Penerapan preprocessing teks dan Multinomial Naïve Bayes pada analisis sentimen [Application of text preprocessing and Multinomial Naïve Bayes in sentiment analysis]. Jurnal Algoritma, 20(1), 89–98.

Prasetyo, S. D., et al. (2023). Komparasi algoritma Naïve Bayes dan KNN pada sentimen relokasi IKN [Comparison of the Naïve Bayes and KNN algorithms on sentiment regarding the relocation of the national capital (IKN)]. Jurnal Teknologi Informasi, 7(1), 40–48.

Prasetyo, V. R., et al. (2023). Analisis sentimen ulasan Cafe Kopi Paste menggunakan Naïve Bayes dan K-Nearest Neighbor [Sentiment analysis of Cafe Kopi Paste reviews using Naïve Bayes and K-Nearest Neighbor]. Jurnal Diterima (Teknologi Informasi dan Ilmu Komputer), 10(3), 511–520.

Putra, E., et al. (2020). Implementasi containerization menggunakan Docker pada arsitektur microservices [Implementation of containerization using Docker in a microservices architecture]. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 4(8), 2600–2608.

Saputra, A. (2026). Sistem rekomendasi coffee shop berdasarkan ulasan Google Maps menggunakan Logistic Regression [Coffee shop recommendation system based on Google Maps reviews using Logistic Regression]. Jurnal Sistem Komputer dan Informatika, 7(2), 180–189.

Sari, P., et al. (2023). Analisis sentimen ulasan aplikasi Fore Coffee menggunakan algoritma Naïve Bayes [Sentiment analysis of Fore Coffee application reviews using the Naïve Bayes algorithm]. Jurnal Sains Komputer & Informatika (J-SAKTI), 7(1), 112–122.

Setiaji, P., & Sastra, R. (2021). Pemodelan perangkat lunak berbasis UML [UML-based software modeling]. Graha Ilmu.

Sianipar, N., et al. (2023). Analisis sentimen opini kereta cepat Jakarta-Bandung menggunakan Naïve Bayes [Sentiment analysis of opinions on the Jakarta–Bandung high-speed train using Naïve Bayes]. Jurnal Eduikasi Informatika, 6(2), 99–107.

Situmorang, H., et al. (2021). Penerapan Waterfall model dalam pengembangan sistem informasi [Application of the Waterfall model in information system development]. Jurnal Tekno Kompak, 15(2), 130–141.

Sofi’ie, M., & Qoiriah, A. (2023). Pengembangan aplikasi web menggunakan Next.js dan React [Web application development using Next.js and React]. Jurnal Manajemen Informatika, 13(1), 55–64.

Stephanie, A., & Irsyad, M. (2024). Penerapan Multinomial Naïve Bayes dalam deteksi cyberbullying pada Instagram [Application of Multinomial Naïve Bayes in cyberbullying detection on Instagram]. Jurnal Media Informatika, 5(1), 15–24.

Ulumi, M., & Perwitasari, A. (2024). Arsitektur client-server dalam pemrograman web modern [Client–server architecture in modern web programming]. Jurnal Informatika Mulawarman, 19(1), 40–47.

Varian, M., et al. (2024). Document level sentiment analysis for Indonesian online reviews. IEEE Access, 12, 14200–14212.

Weske, M. (2019). Business process management: Concepts, languages, architectures. Springer.

Wulandari, R., et al. (2022). Analisis kualitas perangkat lunak menggunakan standard ISO/IEC 25010 [Software quality analysis using the ISO/IEC 25010 standard]. Jurnal Sistem Informasi, 11(2), 75–84.