Sentiment Analysis of User Reviews on the Bus Simulator Indonesia Application Using Machine Learning Approaches

Iswatun  Maimanah; Rakhmad  Maulidi; Dany Candra Febrianto

doi:10.32664/smatika.v16i02.2285

Authors

Iswatun Maimanah Universitas Telkom
Rakhmad Maulidi Universitas Telkom
Dany Candra Febrianto Universitas Telkom

DOI:

https://doi.org/10.32664/smatika.v16i02.2285

Keywords:

Bus Simulator Indonesia, Logistic Regression, Naïve Bayes, Sentiment Analysis, Support Vector Machine

Abstract

User reviews on the Google Play Store serve as a primary source of information for assessing the quality and satisfaction levels of an application. As expectations for game quality and realism continue to rise, Bus Simulator Indonesia still faces a range of technical issues — including bugs, glitches, visual disturbances, and suboptimal controls — that directly impact user comfort and overall experience. This study aims to classify the sentiments expressed by Bus Simulator Indonesia users into three categories: positive, neutral, and negative. In addition, it compares the performance of three machine learning algorithms: Naive Bayes, Support Vector Machine (SVM), and Logistic Regression. The research pipeline consists of data collection, text preprocessing, word weighting, modeling, and model evaluation. The dataset comprises 19,482 Indonesian-language reviews gathered from the Google Play Store between 2021 and 2025, evaluated across three data-splitting scenarios: 90:10, 80:20, and 70:30. The results show that Support Vector Machine consistently achieved the highest accuracy across all scenarios, recording 84.3%, 82.0%, and 81.0%, with weighted F1-score values of 0.83, 0.82, and 0.81, respectively, indicating a more stable classification performance. Logistic Regression followed with accuracies of 81.1%, 79.9%, and 79.0%, with weighted F1-score values of 0.79, 0.78, and 0.77, respectively, while Naive Bayes produced the lowest scores overall. These findings confirm that Support Vector Machine is the most effective algorithm for sentiment classification of Bus Simulator Indonesia user reviews.

References

[1] A. Bahar, T. Astuti, and P. Arsi, “Performance comparison of SVM, Naive Bayes, and support vector machine classification algorithms in analyzing Noice app user reviews,” J. Tek. Inform., vol. 5, no. 4, pp. 469–477, 2024, doi: 10.52436/1.jutif.2024.5.4.2061.

[2] S. Z. Gunawan, “Bus Simulator Indonesia (BUSSID), game buatan lokal rasa internasional,” 2021.

[3] M. F. Ravizaldi, N. Z. Saputra, S. Syabani, and N. Suciana, “Analisis kearifan lokal pada Bus Simulator Indonesia,” in Prosiding Seminar Nasional Desain dan Media, Nov. 2023, pp. 750–755.

[4] T. I. Alfawas, A. Rahim, and R. Rudiman, “Application of TF-IDF feature extraction for sentiment analysis of Bus Simulator Indonesia game reviews using the Naive Bayes algorithm,” J. Soc. Sci. Res., vol. 4, no. 5, pp. 3177–3193, 2024.

[5] S. Imron, E. I. Setiawan, J. Santoso, and M. H. Purnomo, “Aspect based sentiment analysis marketplace product reviews using BERT, LSTM, and CNN,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 3, pp. 586–591, 2023, doi: 10.29207/resti.v7i3.4751.

[6] J. W. Iskandar and Y. Nataliani, “Comparison of Naïve Bayes, SVM, and k-NN for aspect-based gadget sentiment analysis,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 6, pp. 1120–1126, Dec. 2021, doi: 10.29207/resti.v5i6.3588.

[7] R. Maheri, F. N. Salisah, F. Muttakin, and M. Megawati, “Sentiment analysis of M-Paspor application reviews using Naive Bayes and Support Vector Machine,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 10, no. 1, pp. 448–458, 2025, doi: 10.29100/jipi.v10i1.5826.

[8] S. Styawati, A. R. Isnain, N. Hendrastuty, and L. Andraini, “Comparison of Support Vector Machine and Naïve Bayes on Twitter data sentiment analysis,” J. Inform. J. Pengemb. IT, vol. 6, no. 1, pp. 56–60, 2021, doi: 10.30591/jpit.v6i1.3245.

[9] A. Maulana, I. K. Afifah, A. Mubarrak, K. R. Fauzan, A. Dwintara, and B. P. Zen, “Comparison of Logistic Regression, Multinomial NB, SVM, and k-NN methods on sentiment analysis of Gojek app reviews on the Google Play Store,” J. Tek. Inform., vol. 4, no. 6, pp. 1487–1494, Dec. 2023, doi: 10.52436/1.jutif.2023.4.6.863.

[10] S. Setyabudi and E. Aryanny, “Sentiment analysis of Lazada marketplace user ratings with Naïve Bayes and Support Vector Machine methods,” J. Inovtek Polbeng - Seri Inform., vol. 10, no. 1, pp. 422–433, Mar. 2025, doi: 10.35314/sww8cg21.

[11] T. S. Ningsih, T. I. Hermanto, and I. M. Nugroho, “Sentiment analysis of mobile provider application reviews using Naive Bayes algorithm and Support Vector Machine,” SinkrOn, vol. 8, no. 2, pp. 824–835, Mar. 2024, doi: 10.33395/sinkron.v8i2.13469.

[12] Y. Christian, T. Wibowo, and M. Lyawati, “Sentiment analysis by using Naïve Bayes classification and Support Vector Machine, study case Sea Bank,” SinkrOn, vol. 8, no. 1, pp. 258–275, Jan. 2024, doi: 10.33395/sinkron.v9i1.13141.

[13] E. Suryati, Styawati, and A. A. Aldino, “Online transportation sentiment analysis using Word2Vec text embedding feature extraction and Support Vector Machine (SVM) algorithm,” J. Teknol. dan Sist. Inf., vol. 4, no. 1, pp. 96–106, 2023, doi: 10.1109/ISMODE53584.2022.9742906.

[14] M. Prasetya, M. Wulandari, and S. A. Nikmah, “Implementation of basic NLP (natural language processing) in Spotify review sentiment analysis,” in Seminar Nasional Teknologi & Sains, 2024, pp. 145–153.

[15] D. Novira and A. Lattu, “Public sentiment analysis on Instagram regarding the Jakarta-Bandung high-speed train using the Naïve Bayes classifier algorithm,” in Prosiding Seminar Nasional Sistem Informasi dan Manajemen Informatika Universitas Nusa Putra, 2023, pp. 142–149.

[16] N. Hadi and D. Sugiarto, “Sentiment analysis of IKN development on social media X using SVM, Logistic Regression, and Naïve Bayes algorithms,” J. Inform. J. Pengemb. IT, vol. 10, no. 1, pp. 37–49, 2025, doi: 10.30591/jpit.v10i1.7106.

[17] M. F. Madjid, D. E. Ratnawati, and B. Rahayudi, “Sentiment analysis on app reviews using Support Vector Machine and Naïve Bayes classification,” SinkrOn, vol. 7, no. 1, pp. 556–562, Feb. 2023, doi: 10.33395/sinkron.v8i1.12161.

[18] R. Syahputra, G. J. Yanris, and D. Irmayani, “SVM and Naïve Bayes algorithm comparison for user sentiment analysis on Twitter,” SinkrOn, vol. 6, no. 2, pp. 671–678, May 2022, doi: 10.33395/sinkron.v7i2.11430.

[19] J. O. Leandro and M. I. Fianty, “Evaluation of sentiment analysis methods for social media applications: A comparison of Support Vector Machines and Naïve Bayes,” JOIV Int. J. Informatics Vis., vol. 9, no. 2, 2025, doi: 10.62527/joiv.9.2.2905.

[20] A. M. Rizki, B. Bustami, and S. F. Anshari, “Comparison of Support Vector Machine and Naïve Bayes algorithms in sentiment analysis of TikTok Shop application user reviews,” J. Renew. Energy, Electr. Comput. Eng., vol. 5, no. 1, pp. 18–29, 2025, doi: 10.29103/jreece.v5i1.21342.

[21] I. Yunanto and S. Yulianto, “Twitter sentiment analysis PeduliLindungi application using Naïve Bayes and Support Vector Machine,” J. Tek. Inform., vol. 3, no. 4, pp. 807–814, Aug. 2022, doi: 10.20884/1.jutif.2022.3.4.292.

[22] W. Trisnawati and A. Wibowo, “Sentiment analysis of ICT service user using Naive Bayes classifier and SVM methods with TF-IDF text weighting,” J. Tek. Inform., vol. 5, no. 3, pp. 709–719, May 2024, doi: 10.52436/1.jutif.2024.5.3.1784.

[23] L. A. Hayurian and N. Hendrastuty, “Comparison of Naïve Bayes algorithm and Support Vector Machine in sentiment analysis of boycott Israeli products on Twitter,” J. Tek. Inform., vol. 5, no. 3, pp. 731–738, May 2024, doi: 10.52436/1.jutif.2024.5.3.1813.

[24] B. Zhao, “Web scraping,” in Encyclopedia of Big Data, Cham: Springer International Publishing, 2022, pp. 951–953. doi: 10.1007/978-3-319-32010-6_483.

[25] A. B. Muyembe and I. P. Anselemo, “Scientific research sample size determination,” Int. J. Sci. Technol., vol. 11, no. 7, 2023.

[26] Y. K. Singh, Fundamental of Research Methodology and Statistics. New Age International, 2006.

[27] H. T. Duong and T. A. Nguyen-Thi, “A review: preprocessing techniques and data augmentation for sentiment analysis,” Comput. Soc. Networks, vol. 8, no. 1, Dec. 2021, doi: 10.1186/s40649-020-00080-x.

[28] D. A. Tarigan, Z. Situmorang, and R. Rosnelly, “Sentiment analysis of the Play Store Sirekap 2024 application post-presidential election using a comparison of Support Vector Machine (SVM), Naïve Bayes classifier, and random forest methods,” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 3, pp. 661–670, 2025, doi: 10.25126/jtiik.2025129608.

[29] Z. Tang, W. Li, and Y. Li, “An improved supervised term weighting scheme for text representation and classification,” Expert Syst. Appl., vol. 189, p. 115985, 2022, doi: 10.1016/j.eswa.2021.115985.

[30] V. R. Joseph, “Optimal ratio for data splitting,” Feb. 2022, doi: 10.1002/sam.11583.

[31] A. M. Asror and I. K. D. Nuryana, “Prediction and analysis of customer churn at Telkomsel using machine learning approach,” J. Emerg. Inf. Syst. Bus. Intell., vol. 6, no. 2, pp. 230–240, Jul. 2025, doi: 10.26740/jeisbi.v6i2.65825.

[32] T. Gori, A. Sunyoto, and H. Al Fatta, “Data preprocessing and classification for predicting student academic performance,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 1, pp. 215–224, 2024, doi: 10.25126/jtiik.20241118074.

[33] O. Peretz, M. Koren, and O. Koren, “Naive Bayes classifier - An ensemble procedure for recall and precision enrichment,” Eng. Appl. Artif. Intell., vol. 136, p. 108972, 2024, doi: 10.1016/j.engappai.2024.108972.

[34] T. Ke and others, “Maximal margin hyper-sphere SVM for binary pattern classification,” Eng. Appl. Artif. Intell., vol. 117, p. 105615, 2023, doi: 10.1016/j.engappai.2022.105615.

[35] K. Hasanah, “Comparison of sentiment analysis model for Shopee comments on Google Play Store,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 13, no. 1, pp. 21–30, 2024, doi: 10.32736/sisfokom.v13i1.1916.

[36] S. Szabó, I. J. Holb, V. É. Abriha-Molnár, G. Szatmári, S. K. Singh, and D. Abriha, “Classification Assessment Tool: A program to measure the uncertainty of classification models in terms of class-level metrics,” Appl. Soft Comput., vol. 155, p. 111468, 2024, doi: 10.1016/j.asoc.2024.111468.

[37] M. Gultom, J. Marikros, and W. Rusli, “Application of VADER sentiment for detecting English-based sentiment via website,” in Seminar Nasional Corisindo, 2024, pp. 13–18.