PERBANDINGAN METODE NAÏVE BAYES, SUPPORT VECTOR MACHINE DAN RECURRENT NEURAL NETWORK PADA ANALISIS SENTIMEN ULASAN PRODUK E-COMMERCE

Tjut Awaliyah Zuraiyah* -  Universitas Pakuan, Indonesia
Mulyati Mulyati Mulyati -  Ilmu Komputer Universitas Pakuan Bogor, Indonesia
Gilang Haikal Fikri Harahap -  Ilmu Komputer Universitas Pakuan Bogor

DOI : 10.24269/mtkind.v17i1.7092

Abstrak

 Analisis sentimen digunakan sebagai alat bantu untuk mendapatkan pendapat dari konsumen atau masyarakat luas. Ulasan produk pada e-commerce memberikan pengaruh pada penjualan produk. Penelitian ini bertujuan untuk melakukan analisis sentimen terhadap ulasan produk pada platform e-commerce menggunakan algoritma Naïve Bayes, Support Vector Machine (SVM), dan Recurrent Neural Network (RNN). Penelitian juga melibatkan tahapan seleksi data, preprocessing, transformasi, data mining, dan evaluasi/interpretasi. Selain itu, penelitian ini juga bertujuan untuk mengatasi masalah imbalanced data yang terjadi antara sentimen positif dan negatif dengan menerapkan teknik oversampling menggunakan library SMOTE. Dengan melakukan penelitian ini, diharapkan dapat memberikan wawasan dan pemahaman yang lebih baik tentang analisis sentimen dan kontribusinya dalam memahami pendapat konsumen serta meningkatkan keputusan pembelian produk. Dalam penelitian ini, dilakukan analisis sentimen terhadap ulasan produk e-commerce menggunakan algoritma Naïve Bayes, SVM, dan RNN. Data opini diklasifikasikan menjadi positif, negatif, atau netral. Terdapat perbedaan jumlah data antara sentimen positif dan negatif (imbalanced data), yang diperlakukan secara berbeda dalam model. Hasil penelitian menunjukkan bahwa Naïve Bayes memiliki akurasi 86%, SVM memiliki akurasi 88%, dan RNN memiliki akurasi 96% dengan epoch 100.

 

Abstract

 Sentiment analysis serves as a valuable tool for capturing consumer opinions and broader public sentiment. Product reviews posted on e-commerce platforms significantly influence product sales. The objective of this research is to perform sentiment analysis on e-commerce product reviews utilizing Naïve Bayes, Support Vector Machine (SVM), and Recurrent Neural Network (RNN) algorithms. The study encompasses data selection, preprocessing, transformation, data mining, and evaluation/interpretation as crucial stages. Moreover, addressing the issue of imbalanced data, particularly the disparity between positive and negative sentiments, is achieved through the application of oversampling techniques utilizing the SMOTE library. This research aims to enhance the understanding of sentiment analysis, its significance in comprehending consumer opinions, and its role in improving product purchase decisions. The sentiment analysis of e-commerce product reviews was conducted using Naïve Bayes, SVM, and RNN algorithms. The opinions were classified as positive, negative, or neutral. Notably, there is a distinction in the data distribution between positive and negative sentiments (imbalanced data), which necessitates distinct treatment within the models. The findings revealed an accuracy of 86% for Naïve Bayes, 88% for SVM, and 96% for RNN with an epoch of 100.

 

Keywords
Analisis Sentimen, Naïve Bayes, Support Vector Machine, Recurrent Neural Network, SMOTE
  1. N. A. Rakhmawati, A. E. Permana, A. M. Reyhan, and H. Rafli, “Analisa Transaksi Belanja Online Pada Masa Pandemi Covid-19,” J. Teknoinfo, vol. 15, no. 1, p. 32, 2021, doi: 10.33365/jti.v15i1.868.
  2. V. Jain, B. Malviya, and S. Arya, “An Overview of Electronic Commerce (e-Commerce),” J. Contemp. Issues Bus. Gov., vol. 27, no. 3, 2021, doi: 10.47750/cibg.2021.27.03.090.
  3. L. Yue, W. Chen, X. Li, W. Zuo, and M. Yin, “A survey of sentiment analysis in social media,” Knowl. Inf. Syst., vol. 60, no. 2, pp. 617–663, 2019, doi: 10.1007/s10115-018-1236-4.
  4. R. Obiedat, O. Harfoushi, R. Qaddoura, L. Al-Qaisi, and A. M. Al-Zoubi, “An evolutionary-based sentiment analysis approach for enhancing government decisions during covid-19 pandemic: The case of jordan,” Appl. Sci., vol. 11, no. 19, 2021, doi: 10.3390/app11199080.
  5. P. P. A., “Performance Evaluation and Comparison using Deep Learning Techniques in Sentiment Analysis,” J. Soft Comput. Paradig., vol. 3, no. 2, pp. 123–134, 2021, doi: 10.36548/jscp.2021.2.006.
  6. H. Hermanto, A. Mustopa, and A. Y. Kuntoro, “Algoritma Klasifikasi Naive Bayes Dan Support Vector Machine Dalam Layanan Komplain Mahasiswa,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 5, no. 2, pp. 211–220, 2020, doi: 10.33480/jitk.v5i2.1181.
  7. H. Hairani, K. E. Saputro, and S. Fadli, “K-means-SMOTE for handling class imbalance in the classification of diabetes with C4.5, SVM, and naive Bayes,” J. Teknol. dan Sist. Komput., vol. 8, no. 2, pp. 89–93, 2020, doi: 10.14710/jtsiskom.8.2.2020.89-93.
  8. A. Shenoy and A. Sardana, “Multilogue-Net: A Context-Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation,” pp. 19–28, 2020, doi: 10.18653/v1/2020.challengehml-1.3.
  9. S. R. Ahmad, M. Z. M. Rodzi, N. S. Shapiei, N. M. M. Yusop, and S. Ismail, “A review of feature selection and sentiment analysis technique in issues of propaganda,” Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 11, pp. 240–245, 2019, doi: 10.14569/IJACSA.2019.0101132.
  10. R. G, “A Study to Find Facts Behind Preprocessing on Deep Learning Algorithms,” J. Innov. Image Process., vol. 3, no. 1, pp. 66–74, 2021, doi: 10.36548/jiip.2021.1.006.
  11. N. Alvi Hasanah, Nanik Suciati, and Diana Purwitasari, “Pemantauan Perhatian Publik terhadap Pandemi COVID-19 melalui Klasifikasi Teks dengan Deep Learning,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 1, pp. 193–202, 2021, doi: 10.29207/resti.v5i1.2927.
  12. A. Moghar and M. Hamiche, “Stock Market Prediction Using LSTM Recurrent Neural Network,” Procedia Comput. Sci., vol. 170, pp. 1168–1173, 2020, doi: 10.1016/j.procs.2020.03.049.
  13. M. A. Rosid, A. S. Fitrani, I. R. I. Astutik, N. I. Mulloh, and H. A. Gozali, “Improving Text Preprocessing for Student Complaint Document Classification Using Sastrawi,” IOP Conf. Ser. Mater. Sci. Eng., vol. 874, no. 1, 2020, doi: 10.1088/1757-899X/874/1/012017.
  14. X. Pei, F. Mei, and J. Gu, “The real-time state identification of the electricity-heat system based on Borderline-SMOTE and XGBoost,” IET Cyber-Physical Syst. Theory Appl., no. March, pp. 1–11, 2022, doi: 10.1049/cps2.12032.
  15. H. Utama and A. Masruro, “Analisis Sentimen pada Twitter menggunakan Word Embedding dengan Pendekatan Word2Vec,” J. Sist. Cerdas, vol. 05, no. 02, pp. 128–134, 2022.

Full Text:
Article Info
Submitted: 2023-05-02
Published: 2023-07-31
Section: Artikel
Article Statistics: