Optimalisasi Klasifikasi Support Vector Machine dengan SMOTE: Studi Kasus Ulasan Pengguna Aplikasi Alfagift

Isi Artikel Utama

Adhani Mulianti
Yulison Chrisnanto
Herdi Ashaury

Abstrak

Support Vector Machine (SVM) adalah algoritma supervised learning yang bekerja dengan mengklasifikasi berdasarkan kelas yang mengacu pada pola hasil dari proses pelatihan. SVM memiliki beberapa kernel yang umum dan populer digunakan salah satunya adalah kernel linear. Kelemahan SVM adalah dalam “pemilihan parameter” dan performanya cenderung buruk pada kasus dataset yang tidak seimbang. Tujuan penelitian ini adalah untuk mengatasi kelemahan dari algoritma SVM dengan metode yang diusulkanPenelitian ini menggunakan kernel linear dengan ekstraksi fiturnya yaitu Word2Vec dengan model Skip-gram, dan dalam menangani masalah ketidakseimbangan data menggunakan teknik SMOTE (oversampling). Hasil penelitian menunjukkan bahwa dataset yang tidak seimbang menghasilkan akurasi sebesar 90% dan dataset yang seimbang (SMOTE) menghasilkan akurasi sebesar 92%, sehingga teknik oversampling SMOTE terbukti meningkatkan hasil akurasinya sebesar 2%.


 


 

Rincian Artikel

Bagian
Informatika

Referensi

Anam, M. K., Triyani, ;, Fitri, A., Agustin, ;, Lusiana, ;, Muhammad, ;, Firdaus, B., Agus, ;, & Nurhuda, T. (2023). Sentiment Analysis for Online Learning using The Lexicon-Based Method and The Support Vector Machine Algorithm. ILKOM Jurnal Ilmiah, 15(2), 290–302. http://dx.doi.org/10.33096/ilkom.v15i2.1590.290-302

Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L., & Lopez, A. (2020). A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing, 408, 189–215. https://doi.org/10.1016/j.neucom.2019.10.118

Chong, K. S., & Shah, N. (2022). Comparison of Naive Bayes and SVM Classification in Grid-Search Hyperparameter Tuned and Non-Hyperparameter Tuned Healthcare Stock Market Sentiment Analysis. International Journal of Advanced Computer Science and Applications, 13(12), 90–94. https://doi.org/10.14569/IJACSA.2022.0131213

Dey, S., Wasif, S., Tonmoy, D. S., Sultana, S., Sarkar, J., & Dey, M. (2020). 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 2020, 217–220. https://doi.org/10.1109/IC3A48958.2020.233300

Guia, M., Silva, R. R., & Bernardino, J. (2019). Comparison of Naive Bayes, Support Vector Machine, Decision Trees and Random Forest on Sentiment Analysis. IC3K 2019 - Proceedings of the 11th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, 1(Ic3k), 525–531. https://doi.org/10.5220/0008364105250531

Kurniawan, F. W., & Maharani, W. (2020). Indonesian Twitter Sentiment Analysis Using Word2Vec. 2020 International Conference on Data Science and Its Applications, ICoDSA 2020, 31–36. https://doi.org/10.1109/ICoDSA50139.2020.9212906

Mujahid, M., Lee, E., Rustam, F., Washington, P. B., Ullah, S., Reshi, A. A., & Ashraf, I. (2021). Sentiment analysis and topic modeling on tweets about online education during covid-19. Applied Sciences (Switzerland), 11(18). https://doi.org/10.3390/app11188438

Nawangsari, R. P., Kusumaningrum, R., & Wibowo, A. (2019). Word2vec for Indonesian sentiment analysis towards hotel reviews: An evaluation study. Procedia Computer Science, 157, 360–366. https://doi.org/10.1016/j.procs.2019.08.178

Octaviani, K., Andayani Komara, M., & Kurniawan, I. (2022). Analisis Kesuksesan Aplikasi Alfagift Menggunakan Model Delon Dan Mclean Studi Kasus Alfa Express Rest Area Km 72B. Jurnal Informatika, Teknologi Dan Sains, 4(3), 173–178. https://doi.org/10.51401/jinteks.v4i3.1946

Sheik Abdullah, A., Akash, K., ShaminThres, J., & Selvakumar, S. (2021). Sentiment Analysis of Movie Reviews Using Support Vector Machine Classifier with Linear Kernel Function. Advances in Intelligent Systems and Computing, 1176, 345–354. https://doi.org/10.1007/978-981-15-5788-0_34

Sohrabi, M. K., & Hemmatian, F. (2019). An efficient preprocessing method for supervised sentiment analysis by converting sentences to numerical vectors: a twitter case study. Multimedia Tools and Applications, 78(17), 24863–24882. https://doi.org/10.1007/s11042-019-7586-4

Styawati, S., Nurkholis, A., Aldino, A. A., Samsugi, S., Suryati, E., & Cahyono, R. P. (2022). Sentiment Analysis on Online Transportation Reviews Using Word2Vec Text Embedding Model Feature Extraction and Support Vector Machine (SVM) Algorithm. 2021 International Seminar on Machine Learning, Optimization, and Data Science, ISMODE 2021, February 2023, 163–167. https://doi.org/10.1109/ISMODE53584.2022.9742906

Wahyudi, R., & Kusumawardana, G. (2021). Analisis Sentimen pada Review Aplikasi Grab di Google Play Store Menggunakan Support Vector Machine. Jurnal Informatika, 8(2), 200–207. https://doi.org/10.31294/ji.v8i2.9681