Topic Discovery and Sentiment Mapping from Indonesian User Reviews Using NLP and Clustering Techniques
DOI:
https://doi.org/10.24002/jbi.v17i2.14806Keywords:
sentiment analysis, clustering, Honor of Kings, LDA, player reviewsAbstract
The massive volume of unstructured user reviews in mobile games makes manual analysis impractical. Therefore, our study discovers dominant topics and maps sentiments from 8,000 Honor of Kings reviews using an integrated NLP and clustering pipeline. We combine TF-IDF vectorization, mini-batch k-means clustering, and LDA topic modeling, complemented by lexicon-based sentiment analysis. Results identify ten thematic segments reflecting player preferences and technical complaints. Clustering assessment yielded a silhouette score of 0.1071, typical for high-dimensional short-text and indicating soft boundaries, while a chi-square test confirmed a significant association between clusters and sentiment (p < 0.001, Cramér’s V = 0.242). These findings offer practical insights for developers, despite limitations regarding weak cluster separation and low sentiment accuracy in informal text.
Volume umpan balik pengguna yang tidak terstruktur dan masif pada gim seluler membuat analisis manual menjadi tidak praktis. Oleh karena itu, penelitian ini menemukan topik dominan dan memetakan sentimen dari 8.000 ulasan Honor of Kings menggunakan pipeline NLP dan clustering terintegrasi. Kami menggabungkan vektorisasi TF-IDF, clustering mini-batch k-means, dan pemodelan topik LDA, dilengkapi analisis sentimen berbasis leksikon. Hasil mengidentifikasi sepuluh segmen tematik yang mencerminkan preferensi pemain dan keluhan teknis. Penilaian clustering menghasilkan silhouette score 0,1071, yang tipikal untuk teks pendek berdimensi tinggi dan mengindikasikan batas yang lunak, sementara uji chi-square mengonfirmasi asosiasi signifikan antara klaster dan sentimen (p < 0,001, Cramér’s V = 0,242). Temuan ini memberikan wawasan praktis bagi pengembang, meskipun terdapat keterbatasan berupa lemahnya pemisahan klaster dan rendahnya akurasi analisis sentimen pada teks informal.
References
[1] F. Pınarbasi, “Evaluation of Mobile Game Apps Emotional Side: A Sentiment Analysis on Mobile Game App Reviews,” Yönetim Bilimleri Dergisi, vol. 23, no. 58, pp. 1953–1978, Oct. 2025, doi: 10.35408/comuybd.1564966.
[2] J. Dąbrowski, E. Letier, A. Perini, and A. Susi, “Analysing app reviews for software engineering: a systematic literature review,” Empirical Software Engineering, vol. 27, no. 2, p. 43, Mar. 2022, doi: 10.1007/s10664-021-10065-7.
[3] Y. Erlyana, H. Hartono, and J. Y. Lim, “A Scalable NLP-Driven Information System for Multi-Platform Sentiment and Topic Analysis of Indonesian Coffee Brand Reviews,” Informatica, vol. 31, no. 2, pp. 529–538, Feb. 2026, doi: 10.18280/isi.310221.
[4] R. Alghamdi and K. Alfalqi, “A Survey of Topic Modeling in Text Mining,” International Journal of Advanced Computer Science and Applications, vol. 6, no. 1, pp. 134–143, 2015, doi: 10.14569/IJACSA.2015.060121.
[5] V. Fitriyana, Lutfi Hakim, Dian Candra Rini Novitasari, and Ahmad Hanif Asyhar, “Analisis Sentimen Ulasan Aplikasi Jamsostek Mobile Menggunakan Metode Support Vector Machine,” Jurnal Buana Informatika, vol. 14, no. 01, pp. 40–49, Apr. 2023, doi: 10.24002/jbi.v14i01.6909.
[6] R. Purnamasari and A. R. Thaha, “Understanding user satisfaction in digital banking: Sentiment analysis and topic modeling of Indonesian bank reviews,” Business Informatics, vol. 19, no. 3, pp. 101–112, 2025, doi: 10.17323/2587-814X.2025.3.101.112.
[7] S. S. Abdulkhaliq and A. M. Darwesh, “Sentiment Analysis Using Hybrid Feature Selection Techniques,” University of Human Development Journal of Science and Technology, vol. 4, no. 1, pp. 29–40, Feb. 2020, doi: 10.21928/uhdjst.v4n1y2020.pp29-40.
[8] Z. Abidin, A. Junaidi, and Wamiliana, “Text Stemming and Lemmatization of Regional Languages in Indonesia: A Systematic Literature Review,” Journal of Information Systems Engineering and Business Intelligence, vol. 10, no. 2, pp. 217–231, 2024, doi: http://dx.doi.org/10.20473/jisebi.10.2.217-231.
[9] P. Prihatini, I. D. Putra, I. Giriantari, and M. Sudarma, “Stemming Algorithm for Indonesian Digital News Text Processing,” International Journal of Engineering and Emerging Technology, vol. 2, no. 2, Jul. 2017, [Online]. Available: https://garuda.kemdiktisaintek.go.id/documents/detail/1097283
[10] Dewi Fatmarani Surianto and Dewi Fatmawati Surianto, “Enhancing K-Means Clustering for Journal Articles using TF-IDF and LDA Feature Extraction,” Brilliance: Journal of Research and Science Education, vol. 4, no. 2, pp. 964–972, Mar. 2025, doi: 10.47709/brilliance.v4i2.5547.
[11] W. L. Azzahra, J. Indra, R. Rahmat, and S. Faisal, “Sentiment Analysis of User Reviews of the AdaKami Online Loan App from the App Store Using SVM and Naive Bayes,” Journal of Applied Informatics and Computing, vol. 9, no. 3, pp. 838–850, Jun. 2025, doi: 10.30871/jaic.v9i3.9536.
[12] V. H. Pranatawijaya, N. N. K. Sari, R. A. Rahman, E. Christian, and S. Geges, “Unveiling User Sentiment: Aspect-Based Analysis and Topic Modeling of Ride-Hailing and Google Play App Reviews,” Journal of Information Systems Engineering and Business Intelligence, vol. 10, no. 3, pp. 328–339, Oct. 2024, doi: 10.20473/jisebi.10.3.328-339.
[13] C. G. Maurya and S. K. Jha, “Sentiment Analysis: A Hybrid Approach on Twitter Data,” Procedia Computer Science, vol. 235, pp. 990–999, 2024, doi: 10.1016/j.procs.2024.04.094.
[14] A. A. P. Simarmata and T. B. Sasongko, “Sentiment Analysis on BRImo Application Reviews Using IndoBERT,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 3, pp. 851–862, Jun. 2025, doi: 10.30871/jaic.v9i3.8162.
[15] I. Z. Mustaqim and R. R. Suryono, “A Systematic Literature Review of Topic Modeling Techniques in User Reviews,” Journal of Information Systems Engineering and Business Intelligence, vol. 11, no. 2, pp. 238–253, Jul. 2025, doi: 10.20473/jisebi.11.2.238-253.
[16] D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent Dirichlet Allocation,” Journal of Machine Learning Research, vol. 3, pp. 993–1022, 2003.
[17] M. Faisal et al., “Enhancing Indonesian Text Summarization with Latent Dirichlet Allocation and Maximum Marginal Relevance,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 8, pp. 652–661, 2024, doi: 10.14569/IJACSA.2024.0150852.
[18] P. Selvaprasanth, “Unsupervised Topic Discovery and Text Extraction with Generative AI and Embedding Techniques,” Journal of Science Technology and Research (JSTAR), vol. 6, no. 1, 2025.
[19] M. Y. Hidayat, M. A. Yaqin, and Z. Abidin, “Semantic-Enhanced News Clustering Using TF-IDF and WordNet with K-Means,” Journal of Information System and Informatics, vol. 7, no. 4, pp. 3924–3951, Dec. 2025.
[20] S. A. Putri, K. D. Tania, and Naretha Kawadha Pasemah Gumay, “Knowledge Discovery Through Sentiment Analysis and Topic Modeling of BCA Mobile and MyBCA,” Journal of Mathematics, Computations, and Statistics, vol. 8, no. 2, pp. 669–682, Oct. 2025, doi: 10.35580/jmathcos.v8i2.9782.
[21] R. J. Dhanal and V. R. Ghorpade, “Aspect-based sentiment-analysis using topic modelling and machine-learning,” International Journal of Electrical and Computer Engineering, vol. 14, no. 6, p. 6689, Dec. 2024, doi: 10.11591/ijece.v14i6.pp6689-6698.
[22] M. Grootendorst, “BERTopic: Neural topic modeling with a class-based TF-IDF procedure,” Mar. 2022, arXiv: 2203.05794. doi: 10.48550/arXiv.2203.05794.
[23] F. Firdaus et al., “Text clustering for analyzing scientific article using pre-trained language model and k-means algorithm,” Bulletin of Electrical Engineering and Informatics, vol. 14, no. 5, pp. 3728–3740, Oct. 2025, doi: 10.11591/eei.v14i5.9670.
[24] H. Marfani, H. Kamal, A. S. Hussain, and D. Syed, “A comparison of k-means and mini-batch k-means algorithm for customer segregation analysis,” Societal Transformation: AI and Big Data, vol. 3, no. 1, pp. 27–49, Jul. 2025, doi: 10.20547/aibd.253103.
[25] F. Iglesias Vázquez and T. Zseby, “Temporal silhouette: validation of stream clustering robust to concept drift,” Machine Learning, vol. 113, no. 4, pp. 2067–2091, Apr. 2024, doi: 10.1007/s10994-023-06462-2.
[26] C. Tang, “Review on Application of Chi-square Statistic in Text Classification in Recent Five Years,” Academic Journal of Engineering and Technology, vol. 97, no. 1, pp. 115–118, Nov. 2024, doi: 10.54254/2755-2721/97/20241397.
[27] Y. Ortakci and B. Borhan, “Optimizing SBERT for long text clustering: two novel approaches with empirical insights,” The Journal of Supercomputing, vol. 81, no. 8, p. 950, Jun. 2025, doi: 10.1007/s11227-025-07414-4.
[28] C. Shi, B. Wei, S. Wei, W. Wang, H. Liu, and J. Liu, “A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm,” EURASIP Journal on Wireless Communications and Networking, vol. 2021, no. 1, p. 31, Dec. 2021, doi: 10.1186/s13638-021-01910-w.
[29] J. Cohen, Statistical power analysis for the behavioral sciences, 2nd ed. Hillsdale, N.J: L. Erlbaum Associates, 1988.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright of this journal is assigned to Jurnal Buana Informatika as the journal publisher by the knowledge of author, whilst the moral right of the publication belongs to author. Every printed and electronic publications are open access for educational purposes, research, and library. The editorial board is not responsible for copyright violation to the other than them aims mentioned before. The reproduction of any part of this journal (printed or online) will be allowed only with a written permission from Jurnal Buana Informatika.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
