PENERAPAN METODE SUPPORT VECTOR MACHINE DAN NAÏVE BAYES PADA KLASIFIKASI SENTIMEN REVIEW APLIKASI WHATSAPP
Article Sidebar
Read Counter : 2
Download : 2
Main Article Content
Abstract
With the growing popularity of user-driven applications like WhatsApp, there is a growing need to analyze user sentiment effectively. In this research, we apply the Support Vector Machine (SVM) method to analyze the sentiment of WhatsApp user reviews on the Google Play Store. Validation data is processed and normalized before being applied to the SVM model. Text representation with the TF-IDF technique is used to produce relevant features. Experiments are carried out by dividing the data into a training set and a testing set. The model evaluation results show the effectiveness of SVM in sentiment classification, and accuracy and other evaluation metrics provide satisfactory results. This application of SVM in sentiment analysis contributes to a deep understanding of user reactions to the WhatsApp application and provides valuable insights for developers and stakeholders. Experiments were carried out to compare the performance of the two algorithms, including accuracy, precision, recall and F1 score. Experimental results show that both algorithms can provide good emotion classification, but their performance may vary depending on the type of dataset and parameters used. This study contributes to understanding user sentiment towards WhatsApp and provides insights to developers to improve the quality of their applications. In addition, the experimental results provide deeper insights into the advantages and disadvantages of Naive Bayes and SVM in the context of sentiment classification in application reviews.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Menawarkan akses terbukaReferences
[1] Tetsuya Nasukawa, J. Y. (2003). Sentiment analysis: capturing favorability using natural language processing. In Proceedings of the 2nd international conference on Knowledge capture, 70-77.
[2] Cortes, .. V. (1995). Support Vector Machine. Machine Learning, 273-297.
[3] Barokah, K. (2019). Metode Naive Bayes dari teorema Bayes adalah. 10.
[4] Wijaya, W. D. (2022). Penerapan metode Support Vector Machine untuk analisis sentimen pada ulasan pelanggan hotel di tripadvisor. jurnal Ilmu Komputer dan Sistem Informasi, 10.2
[5] Yan Kenny, D. A. (2022). Analisis sentimen komentar netizen twitter terhadap kesehatan mental masyarakat Indonesia. Jurnal Ilmu Komputer Dan Sistem Informasi, 10.1.
[6] Gunawan, B., Sastypratiwi, H., & Pratama, E. E. (2018). (Gunawan, 2018). JEPIN (Jurnal Edukasi dan Penelitian Informatika), 4(2), 113-118.
[7] Nugroho, D. G. (2016). analisis sentimen pada jasa ojek online menggunakan metode naive bayes. Prosiding seminar sains nasional dan teknologi, Vol. 1, no. 1.
[8] Sipayung, E. M., Maharani, H., & Zefanya, I. (2016). Perancangan Sistem Analisis Sentimen Komentar Pelanggan Menggunakan Metode Naive Bayes Classifier. Jurnal Sistem Informasi (JSI), 8(1), 958-965.
[9] Yulita, W. (2021). Analisis sentimen terhadap opini masyarakat tentang vaksin covid-19 menggunakan algoritma naïve bayes classifier. jurnal data mining dan sistem informasi, 1-9.
[10] Tuhuteru, H. (2020). Analisis Sentimen Masyarakat Terhadap Pembatasan Sosial Berksala Besar Menggunakan Algoritma Support Vector Machine. Journal Information System Development (ISD), 5(2)
[11] Styawati, S. H. (2021). analisis sentimen masyarakat terhadap program kartu prakerja pada twitter dengan metode support vector machine. jurnal informatika: jurnal pengembangan it, 150-155.
[12] Novantirani, A. S. (2015). Analisis sentimen pada twitter untuk mengenai perubahan trasnportasi umum darat dalam kota dengan metode support vector machine. eProceedings of engineering, 2(1).
[13] Irfani, F. F. (2020). analisis sentimen review aplikasi ruang guru menggunakan algoritma support vector machine. JBMI, 258.
[14] Rofiqoh, U. P. (2017). analisis sentimen tingkat kepuasan pengguna penyedia layanan telekomunikasi seluler indonesia pada twitter dengan metode support vector machine dan lexicon based features. jurnal pengembangan teknologi informasi dan ilmu komputer , 1725-1732.
[15] Arsi, P., & Waluyo, R. (2021). Analisis Sentimen Wacana Pemindahan Ibu Kota Indonesia Menggunakan Algoritma Support Vector Machine (SVM). J. Teknol. Inf. dan Ilmu Komput, 8(1), 147.
[16] Apriyani, H. &. (2020). perbandingan metode naive bayes dab support vector machine. journal of information technology ampera, 133-143.
[17] Sari, C. A. (2022). Perbandingan Metode Naïve Bayes, Support Vector Machine Dan Decision Tree Dalam Klasifikasi Konsumsi Obat. Jurnal Litbang Edusaintech, 33-41.
[18] Lasulika, M. E. (2019). Komparasi Naïve Bayes, Support Vector Machine Dan K-Nearest Neighbor Untuk Mengetahui Akurasi Tertinggi Pada Prediksi Kelancaran Pembayaran Tv Kabel. ILKOM Jurnal Ilmiah,, 11-16.
[19] Robertson, S. (2004). Understanding inverse document frequency : on theoritical arguments for IDF. Journal of documentation 60.5, 503 - 520.
[20] Ismuhamdan, M. E.-1. (Ismuhamdan, M. E., Prajoko, P., & Apriandari, W. (2023)). Klasifikasi Efektivitas Kebijakan Relokasi Pusat Jajanan Kota Sukabumi Menggunakan Algoritma Naïve Bayes Classifier. Bit (Fakultas Teknologi Informasi Universitas Budi Luhur), 20(2), 103-112.