Sentiment Analysis of Duolingo App User Reviews on Google Play Store Using Naive Bayes Algorithm
Article Sidebar
Main Article Content
Abstract
The advancement of digital technology has driven the widespread use of mobile-based language learning applications, such as Duolingo, which has become one of the most popular educational platforms globally. As the user base grows, reviews on platforms like Google Play Store serve as a valuable data source for evaluating service quality. This study aims to analyze user review sentiments on Duolingo using the Multinomial Naive Bayes algorithm and assess its performance in classifying positive and negative sentiments. A quantitative approach involving text mining and classification was employed. A total of 1,000 Indonesian-language reviews were collected via web scraping. The analysis involved preprocessing steps including tokenization, stopword removal, stemming, and TF-IDF vectorization, followed by an 80:20 train-test data split. Results showed an accuracy of 77.78%, with a high f1-score for positive sentiment (0.87) but extremely low for negative sentiment (0.05). This imbalance stems from skewed class distribution and the model’s limited ability to capture linguistic context. The study highlights the limitations of classical algorithms in Indonesian-language sentiment analysis and recommends advanced approaches such as data balancing, manual labeling, and the use of context-aware models like BERT to produce more accurate and fair opinion analytics.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] Statista, “Most downloaded language learning apps worldwide,” Statista.com, 2024. [Online]. Available: https://www.statista.com
[2] B. Pang and L. Lee, “Opinion mining and sentiment analysis,” Foundations and Trends in Information Retrieval, vol. 2, no. 1–2, pp. 1–135, 2008.
[3] V. Kumar and T. M. Sebastian, “Sentiment analysis: A perspective on Naive Bayes classifier,” in Proc. Int. Conf. on Computer Applications, 2012, pp. 1–4.
[4] T. A. Sandy, A. Ghufron, and A. Muhtadi, “Text classification of Duolingo reviews on Google Play: Insights for enhancing M-learning applications,” Int. J. Emerg. Technol. Learn. (iJET), vol. 20, no. 5, pp. 102–115, 2025.
[5] R. F. Firdaus, O. N. Pratiwi, and I. Y. Mukti, “Sentiment analysis and topic modeling for Duolingo application on Google Play Store,” in Proc. 2024 Int. Conf. on Data Science and Artificial Intelligence (ICDSAI), IEEE, 2024.
[6] B. Liu, Sentiment Analysis and Opinion Mining. San Rafael, CA: Morgan & Claypool Publishers, 2012.
[7] M. J. Salganik, Bit by Bit: Social Research in the Digital Age. Princeton, NJ: Princeton University Press, 2017.
[8] D. Lazer et al., “Computational social science,” Science, vol. 323, no. 5915, pp. 721–723, 2009, doi: 10.1126/science.1167742.
[9] R. Mitchell, Web Scraping with Python: Collecting Data from the Modern Web, 2nd ed., Sebastopol, CA: O’Reilly Media, 2018.
[10] A. McCallum and K. Nigam, “A comparison of event models for Naive Bayes text classification,” in Proc. AAAI 98 Workshop on Learning for Text Categorization, Madison, WI, USA, Jul. 1998, pp. 41–48.
[11] H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Trans. Knowl. Data Eng., vol. 21, no. 9, pp. 1263–1284, Sept. 2009, doi: 10.1109/TKDE.2008.239.
[12] A. Hidayatullah and A. P. Wibowo, “Studi komparatif algoritma klasifikasi Naive Bayes dan K-Nearest Neighbor dalam sentiment analysis ulasan produk Tokopedia,” J. RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 4, no. 2, pp. 285–292, Apr. 2020, doi: 10.29207/resti.v4i2.2031.
[13] J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA, Jun. 2019, pp. 4171–4186, doi: 10.48550/arXiv.1810.04805.
[14] Y. Asri, W. N. Suliyanti, D. Kuswardani, and M. Fajri, “Pelabelan Otomatis Lexicon Vader dan Klasifikasi Naive Bayes dalam menganalisis sentimen data ulasan PLN Mobile,” Petir, vol. 15, no. 2, pp. 264–275, 2022, doi: 10.33322/petir.v15i2.1733.
[15] T. A. Sari, E. Sinduningrum, and F. Noor Hasan, “KLIK: Kajian Ilmiah Informatika dan Komputer Analisis Sentimen Ulasan Pelanggan Pada Aplikasi Fore Coffee Menggunakan Metode Naïve Bayes,” Media Online), vol. 3, no. 6, pp. 773– 779, 2023, doi: 10.30865/klik.v3i6.884.
[16] R. Wahyudi and G. Kusumawardana, “Analisis Sentimen pada Aplikasi Grab di Google Play Store Menggunakan Support Vector Machine,” J. Inform., vol. 8, no. 2, pp. 200–207, 2021, doi: 10.31294/ji.v8i2.9681.
[17] M. Diki Hendriyanto, A. A. Ridha, and U. Enri, “Analisis Sentimen Ulasan Aplikasi Mola Pada Google Play Store Menggunakan Algoritma Support Vector Machine Sentiment Analysis of Mola Application Reviews on Google Play Store Using Support Vector Machine Algorithm,” J. Inf. Technol. Comput. Sci., vol. 5, no. 1, pp. 1–7, 2022.
[18] A. Nurian, “Analisis Sentimen Ulasan Pengguna Aplikasi Google Play Menggunakan Naïve Bayes,” J. Inform. dan Tek. Elektro Terap., vol. 11, no. 3s1, pp. 829–835, 2023, doi: 10.23960/jitet.v11i3s1.3348.
[19] T. A. Sandy, A. Ghufron, and A. Muhtadi, “Text classification of Duolingo reviews on Google Play: Insights for enhancing M-learning applications,” Int. J. Emerg. Technol. Learn. (iJET), vol. 20, no. 5, pp. 102–115, 2025. [Online]. Available: https://search.ebscohost.com/login.aspx?direct=true&profile=ehost&scope=site&authtype=crawler&jrnl=18657923&AN=184462183
[20] R. F. Firdaus, O. N. Pratiwi, and I. Y. Mukti, “Sentiment analysis and topic modeling for Duolingo application on Google Play Store,” in Proc. 2024 Int. Conf. Data Sci. Artif. Intell. (ICDSAI), IEEE, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10913140