Topic Identification of InterActive QRIS Application User Reviews Using Probabilistic Latent Semantic Analysis (PLSA)
Keywords:
InterActive QRIS, Topic Identification, PLSAAbstract
The growth of digital payment systems has driven the increasing adoption of the Quick Response Code Indonesian Standard (QRIS). One application providing this service is InterActive QRIS, available on the Google Play Store. Users can submit text reviews containing opinions and experiences with the application, but such data is unstructured and thus difficult to analyze manually. This study aims to identify topics and analyze their distribution and dominance in InterActive QRIS user reviews using Probabilistic Latent Semantic Analysis (PLSA), with parameter estimation via the Expectation-Maximization (EM) algorithm. The data were analyzed through text preprocessing, construction of the Bag of Words (BoW) and Document-Term Matrix (DTM), model fitting, and model evaluation. Preprocessing yielded 4,524 reviews with 1,969 unique words, represented as a 4,524 × 1,969 DTM. PLSA models were fitted for K = 2 to K = 10, all of which converged successfully. Based on quantitative evaluation using perplexity and qualitative evaluation of topic interpretability, the optimal number of topics was K = 6, with a perplexity value of 175.3581. The six resulting topics were: (1) account access and security issues, (2) system issues in the QRIS transaction process, (3) issues in the user registration and verification process, (4) customer service responsiveness issues, (5) user satisfaction with QRIS, and (6) issues in fund withdrawal and account balance processes. Overall, topics representing application usage issues accounted for 77.32% of all reviews, while the topic representing user satisfaction with QRIS accounted for 22.66%. These findings can serve as an evaluation basis for InterActive QRIS developers in understanding the needs and issues most commonly experienced by users.
References
D. Y. Yusuf and S. Kristiyanto, “Transaksi Digital Perbankan dan Dampaknya dengan Perekonomian Indonesia,” Economie: Jurnal Ilmu Ekonomi, vol. 3, no. 2, p. 138, Jan. 2022, doi: 10.30742/economie.v3i2.1815.
Untoro, P. R. Widodo, and Arifin MS, “Kajian Penggunaan Instrumen Sistem Pembayaran sebagai Leading Indicator Makroekonomi,” 2014.
Bank Indonesia, “ Statistik Sistem Pembayaran dan Infrastruktur Pasar Keuangan (SPIP) Statistik Sistem Pembayaran dan Infrastruktur Pasar Keuangan (SPIP),” Bank Indonesia.
SNKI, “Quick Response Code Indonesian Standard (QRIS),” Strategi Nasional Keuangan Inklusif (SNKI).
ASPI, “Statistik QRIS,” Asosiasi Sistem Pembayaran Indonesia (ASPI).
A. C. Sari and H. H. Adinugraha, “Implementation of QRIS-Based Payments Towards the Digitalization of Indonesian MSMEs,” Ekonomika Syariah : Journal of Economic Studies, vol. 5, no. 2, Jan. 2022, doi: 10.30983/es.v5i2.5027.
A. Septiani, “QRIS Dinanti di Luar Negeri, Dikeluhkan Sebagian Kalangan di Negeri Sendiri,” Kantor Berita Radio (KBR) Indonesia. [Online]. Available: https://kbr.id/articles/indeks/qris-dinanti-di-luar-negeri-dikeluhkan-sebagian-kalangan-di-negeri-sendiri
Interactive QRIS, “Modus Phishing QRIS : Kenali Modus dan Cara Menghindarinya di Lapangan,” InterActive QRIS. [Online]. Available: https://qris.interactive.co.id/homepage/blog-detail.php?lang=id&page=MTk5-modus-phishing-qris---kenali-modus-dan-cara-menghindarinya-di-lapangan
E. Supriyadi and P. N. Makatita, “Sentiment Analysis of TikTok User Comments on QRIS Adoption in Indonesia Using IndoBERT,” Procedia Comput. Sci., vol. 269, pp. 121–130, 2025, doi: 10.1016/j.procs.2025.08.265.
C. Zong, R. Xia, and J. Zhang, Text Data Mining. Singapore: Springer Singapore, 2021. doi: 10.1007/978-981-16-0100-2.
D. Oneață, “Probabilistic Latent Semantic Analysis,” 2011.
S. N. Ahmad and M. Laroche, “Extracting marketing information from product reviews: a comparative study of latent semantic analysis and probabilistic latent semantic analysis,” Journal of Marketing Analytics, vol. 11, no. 4, pp. 662–676, Dec. 2023, doi: 10.1057/s41270-023-00218-6.
D. Khotimah and R. Sarno, “Sentiment Analysis of Hotel Aspect Using Probabilistic Latent Semantic Analysis, Word Embedding and LSTM,” International Journal of Intelligent Engineering and Systems, vol. 12, no. 4, pp. 275–290, Aug. 2019, doi: 10.22266/ijies2019.0831.26.
V. B. Kobayashi, S. T. Mol, H. A. Berkers, G. Kismihók, and D. N. Den Hartog, “Text Mining in Organizational Research,” Organ. Res. Methods, vol. 21, no. 3, pp. 733–765, Jul. 2018, doi: 10.1177/1094428117722619.
D. Prawira, N. Mutiah, and I. Rusi, Pengantar Text Mining dan Implementasinya. UNTAN Press, 2019.
A. D. M. Putri, N. Sulistianingsih, and R. Rismayati, “Pengaruh Teknik Representasi Teks Bag-of-Words dan TF-IDF terhadap Akurasi Klasifikasi Sentimen Teks Multi-Domain,” JTIM : Jurnal Teknologi Informasi dan Multimedia, vol. 7, no. 4, pp. 675–688, Oct. 2025, doi: 10.35746/jtim.v7i4.756.
T. Hoffman, “Probabilistic Latent Semantic Analysis,” Proceedings of the Fifteenth Conference, 1999.
David. M. Blei, Y. N. Andrew, and Michael. I. Jordan, “Latent Dirichlet Allocation,” Journal of Machine Learning Research, pp. 993–1022, 2003.
S. N. Sari, B. G. Pratama, and R. Prastowo, “Penggunaan Metode Elbow untuk Pemilihan Jumlah Klaster dalam Identifikasi Bahan Material Shelter Modular,” Prosiding Seminar Nasional ReTII ke-19 (Edisi Penelitian), pp. 157–163, 2024.
