Analisis Sentimen dan Pemodelan Topik Terhadap Ulasan Aplikasi Jenius Menggunakan Metode Support Vector Machine dan Latent Dirichlet Allocation
Kata Kunci:
analisis sentimen, pemodelan topik, SVM, LDA, ulasan, JeniusAbstrak
Jenius, aplikasi perbankan digital populer di Google Play Store, telah mendapatkan banyak ulasan dari penggunanya. Sayangnya, dengan banyaknya ulasan dan keterbatasan sumber daya manusia, proses evaluasi akan menghabiskan banyak waktu dan berpotensi menghambat pengambilan keputusan yang tepat. Oleh karena itu, diperlukan model pembelajaran mesin untuk melakukan analisis sentimen dan topik pemodelan secara otomatis. Informasi yang diekstrak dari ulasan negatif dapat digunakan untuk memperbaiki sistem yang ada, sedangkan informasi yang diekstrak dari ulasan positif dapat digunakan untuk mempertahankan sistem yang berjalan. Tahapan penelitian meliputi pengumpulan data, prapemrosesan data, pelabelan data, ekstraksi fitur, klasifikasi sentimen, pemodelan topik, evaluasi, dan validasi topik. Data menunjukkan sebaran ulasan bersentimen positif, negatif, dan netral berturut-turut sebanyak 50.1%, 45.8%, 4.2%. Model klasifikasi sentimen dibangun menggunakan algoritma SVM dari 8508 data ulasan. Hasil penelitian menunjukkan bahwa model klasifikasi sentimen terbaik memiliki nilai accuracy sebesar 94.03% dan f1-score sebesar 93.99%. Selain itu, peneliti menggunakan LDA untuk mengidentifikasi topik bahasan pada ulasan Jenius. Hasil evaluasi LDA menunjukkan bahwa model dengan jumlah topik lima memberikan nilai coherence terbaik sebesar 55.78% (model ulasan negatif) dan 63.59% (model ulasan positif). Interpretasi hasil pemodelan topik ulasan negatif menunjukkan tiga aspek yang sering dibahas yaitu kualitas sistem (30,4% atau 2475 ulasan), kualitas informasi (15,6% atau 1271 ulasan), dan kualitas layanan (1,8% atau 148 ulasan). Beberapa pengguna mengungkapkan kekecewaan terhadap performa aplikasi, biaya dan denda layanan keuangan yang tinggi, serta layanan dukungan pelanggan yang rumit. Sebaliknya, dalam ulasan positif, kualitas sistem menjadi aspek yang paling dominan, mencakup 52,2% (4259 ulasan), dengan pengguna merasa puas terhadap kemudahan transaksi dan tampilan yang sederhana.
Referensi
Aftab, F., Bazai, S. U., Marjan, S., Baloch, L., Aslam, S., Amphawan, A., & Neo, T.-K. (2023). A Comprehensive Survey on Sentiment Analysis Techniques. International Journal of Technology, 6, 1288-1298. doi:https://doi.org/10.14716/ijtech.v14i6.6632
DeLone, W. H., & McLean, E. R. (2016, Aug 25). Information Systems Success Measurement. Foundations and Trends® in Information Systems, 2(1), 1-116. doi:http://dx.doi.org/10.1561/2900000005
Dey, S., Wasif, S., Tonmoy, D. S., Sultana, S., Sarkar, J., & Dey, M. (2020, February 05-07). A Comparative Study of Support Vector Machine and Naive Bayes Classifier for Sentiment Analysis on Amazon Product Reviews. 2020 International Conference on Contemporary Computing and Applications (IC3A), 217-220. doi:https://doi.org/10.1109/IC3A48958.2020.233300
Dhammananda, J., Budi, I., & Santoso, A. B. (2023, August 9-10). Sentiment Analysis and Topic Modeling of E-grocery Application Reviews Using Naive Bayes and Support Vector Machine: A Case Study of Segari Data Review on the Google Play Store. 2023 3rd International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), 13-18. doi:https://doi.org/10.1109/ICE3IS59323.2023.10335206
Karabiber, F. (n.d.). TF-IDF — Term Frequency-Inverse Document Frequency. Retrieved Oktober 6, 2023, from LearnDataSci: https://www.learndatasci.com/glossary/tf-idf-term-frequency-inverse-document-frequency/
Mifrah, S., & Benlahmar, E. H. (2020, August). Topic Modeling Coherence: A Comparative Study between LDA and NMF Models using COVID’19 Corpus. International Journal of Advanced Trends in Computer Science and Engineering, 9, 5756-5761. doi:https://doi.org/10.30534/ijatcse/2020/231942020
Murshed, B. A., Mallappa, S., Abawajy, J., Saif, M. A., Al ariki, H. D., & Abdulwahab, H. M. (2023). Short text topic modelling approaches in the context of big data: taxonomy, survey, and analysis. Artifcial Intelligence Review, 56, 5133-5260. doi:https://doi.org/10.1007/s10462-022-10254-w
Nurlinda, R., & Bertuah, E. (2022). EVALUATION OF SUCCESSFUL MOBILE BANKING INFORMATION. Jurnal Ekonomi dan Manajemen, 16(2), 77-85. doi:https://doi.org/10.30650/jem.v16i2.3607
Qader, W. A., M.Ameen, M., & Ahmed, B. I. (2019). An Overview of Bag of Words;Importance, Implementation, Applications, and Challenges. Fifth International Engineering Conference on Developments in Civil & Computer Engineering Applications 2019 - (IEC2019), 200-204. doi:https://doi.org/10.1109/IEC47844.2019.8950616
Rana, J., Gaur, L., & Santosh, K. (2022). Classifying Customers’ Journey from Online Reviews of Amazon Fresh via Sentiment Analysis and Topic Modelling. 2022 3rd International Conference on Computation, Automation and Knowledge Management (ICCAKM), 1-6. doi:https://doi.org/10.1109/ICCAKM54721.2022.9990124
Wankhade, M., Rao, A. C., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications,. Artifcial Intelligence Review (2022) 55:5731–5780, 55, 5731–5780. doi:https://doi.org/10.1007/s10462-022-10144-1
Wisnu, G. R., Ahmadi, Muttaqi, A. R., Santoso, A. B., Putra, P. K., & Budi, I. (2020). Sentiment Analysis and Topic Modelling of 2018 Central Java Gubernatorial Election using Twitter Data. 2020 International Workshop on Big Data and Information Security (IWBIS), 35-40. doi:https://doi.org/10.1109/IWBIS50925.2020.9255583
Zebari, R. R., Abdulazeez, A. M., Zeebaree, D. Q., Zebari, D. A., & Saeed, J. N. (2020, Mei 15). A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction. Journal of Applied Science and Technology Trends (JASTT), 1(1), 56 - 70. doi:https://doi.org/10.38094/jastt1224
Zvornicanin, E. (2024, March 18). When Coherence Score Is Good or Bad in Topic Modeling? (E. Martin, Editor) Retrieved from Baeldung: https://www.baeldung.com/cs/topic-modeling-coherence-score
Aftab, F., Bazai, S. U., Marjan, S., Baloch, L., Aslam, S., Amphawan, A., & Neo, T.-K. (2023). A Comprehensive Survey on Sentiment Analysis Techniques. International Journal of Technology, 6, 1288-1298. doi:https://doi.org/10.14716/ijtech.v14i6.6632
DeLone, W. H., & McLean, E. R. (2016, Aug 25). Information Systems Success Measurement. Foundations and Trends® in Information Systems, 2(1), 1-116. doi:http://dx.doi.org/10.1561/2900000005
Dey, S., Wasif, S., Tonmoy, D. S., Sultana, S., Sarkar, J., & Dey, M. (2020, February 05-07). A Comparative Study of Support Vector Machine and Naive Bayes Classifier for Sentiment Analysis on Amazon Product Reviews. 2020 International Conference on Contemporary Computing and Applications (IC3A), 217-220. doi:https://doi.org/10.1109/IC3A48958.2020.233300
Dhammananda, J., Budi, I., & Santoso, A. B. (2023, August 9-10). Sentiment Analysis and Topic Modeling of E-grocery Application Reviews Using Naive Bayes and Support Vector Machine: A Case Study of Segari Data Review on the Google Play Store. 2023 3rd International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), 13-18. doi:https://doi.org/10.1109/ICE3IS59323.2023.10335206
Karabiber, F. (n.d.). TF-IDF — Term Frequency-Inverse Document Frequency. Retrieved Oktober 6, 2023, from LearnDataSci: https://www.learndatasci.com/glossary/tf-idf-term-frequency-inverse-document-frequency/
Mifrah, S., & Benlahmar, E. H. (2020, August). Topic Modeling Coherence: A Comparative Study between LDA and NMF Models using COVID’19 Corpus. International Journal of Advanced Trends in Computer Science and Engineering, 9, 5756-5761. doi:https://doi.org/10.30534/ijatcse/2020/231942020
Murshed, B. A., Mallappa, S., Abawajy, J., Saif, M. A., Al ariki, H. D., & Abdulwahab, H. M. (2023). Short text topic modelling approaches in the context of big data: taxonomy, survey, and analysis. Artifcial Intelligence Review, 56, 5133-5260. doi:https://doi.org/10.1007/s10462-022-10254-w
Nurlinda, R., & Bertuah, E. (2022). EVALUATION OF SUCCESSFUL MOBILE BANKING INFORMATION. Jurnal Ekonomi dan Manajemen, 16(2), 77-85. doi:https://doi.org/10.30650/jem.v16i2.3607
Qader, W. A., M.Ameen, M., & Ahmed, B. I. (2019). An Overview of Bag of Words;Importance, Implementation, Applications, and Challenges. Fifth International Engineering Conference on Developments in Civil & Computer Engineering Applications 2019 - (IEC2019), 200-204. doi:https://doi.org/10.1109/IEC47844.2019.8950616
Rana, J., Gaur, L., & Santosh, K. (2022). Classifying Customers’ Journey from Online Reviews of Amazon Fresh via Sentiment Analysis and Topic Modelling. 2022 3rd International Conference on Computation, Automation and Knowledge Management (ICCAKM), 1-6. doi:https://doi.org/10.1109/ICCAKM54721.2022.9990124
Wankhade, M., Rao, A. C., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications,. Artifcial Intelligence Review (2022) 55:5731–5780, 55, 5731–5780. doi:https://doi.org/10.1007/s10462-022-10144-1
Wisnu, G. R., Ahmadi, Muttaqi, A. R., Santoso, A. B., Putra, P. K., & Budi, I. (2020). Sentiment Analysis and Topic Modelling of 2018 Central Java Gubernatorial Election using Twitter Data. 2020 International Workshop on Big Data and Information Security (IWBIS), 35-40. doi:https://doi.org/10.1109/IWBIS50925.2020.9255583
Zebari, R. R., Abdulazeez, A. M., Zeebaree, D. Q., Zebari, D. A., & Saeed, J. N. (2020, Mei 15). A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction. Journal of Applied Science and Technology Trends (JASTT), 1(1), 56 - 70. doi:https://doi.org/10.38094/jastt1224
Zvornicanin, E. (2024, March 18). When Coherence Score Is Good or Bad in Topic Modeling? (E. Martin, Editor) Retrieved from Baeldung: https://www.baeldung.com/cs/topic-modeling-coherence-score
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
