Analysis of machine learning approaches to determine online shopping ratings using naïve bayes and svm

Muit Sunjaya; Zulham Sitorus; Khairul; Muhammad Iqbal; A.P.U Siahaan

doi:10.61306/ijecom.v3i1.60

Authors

Muit Sunjaya Universitas Pembangunan Panca Budi
Zulham Sitorus Universitas Pembangunan Panca Budi
Khairul Universitas Pembangunan Panca Budi
Muhammad Iqbal Universitas Pembangunan Panca Budi
A.P.U Siahaan Universitas Pembangunan Panca Budi

DOI:

https://doi.org/10.61306/ijecom.v3i1.60

Keywords:

Naïve Bayes, Support Vector Machine, sentiment analysis, classification, machine learning, lazada

Abstract

This research aims to identify and compare the effectiveness of Naïve Bayes and Support Vector Machine (SVM) algorithms in classifying ratings based on customer comments on the Lazada online shopping platform. The main issues identified include data uncertainty, model selection and optimization, as well as improving efficiency and scalability. Using a dataset of comments and reviews from Lazada, this study conducts an analysis using both algorithms to determine which is most effective in classifying comments into appropriate ratings. The research methodology includes data collection, text preprocessing, algorithm implementation, and evaluation using a confusion matrix to measure accuracy, precision, recall, and F-measure. This analysis is supported by data visualization using Python, allowing for in-depth interpretation and understanding of the results. The research findings show significant differences in the performance of both algorithms, with each having strengths in certain aspects of classification. The discussion in this study interprets these results to address the research questions formulated and demonstrates the practical application of machine learning theory in real-world data processing. This study concludes that both algorithms have significant potential in sentiment classification but require further adjustment and optimization to improve accuracy and efficiency. Recommendations for further research include the development of hybrid models or new approaches that can address the identified limitations, as well as exploration of more diverse datasets to test the scalability of the proposed solutions.

References

Adijaya, M.Y. 2020. Implementasi Reduced Support Vector Machines Dalam Sistem Deteksi Kepribadian Berdasarkan Pola Tanda Tangan.

Amelia, R.D., Michael, M. & Mulyandi, R. 2021. Analisis Online Consumer Review Terhadap Keputusan Pembelian pada E-Commerce Kecantikan. Jurnal Indonesia Sosial Teknologi, 2(2): 274–280.

Buntoro, G.A. 2017. Analisis Sentimen Calon Gubernur DKI Jakarta 2017 Di Twitter. INTEGER: Journal of Information Technology, 2(1).

Cavalin, P. & Oliveira, L. 2018. Confusion matrix-based building of hierarchical classification. Iberoamerican Congress on Pattern Recognition. Springer, hal.271–278.

Chaffey, D., Edmundson-Bird, D. & Hemphill, T. 2019. Digital business and e-commerce management. Pearson UK.

Darmawan, A., Kustian, N. & Rahayu, W. 2018. Implementasi Data Mining Menggunakan Model SVM untuk Prediksi Kepuasan Pengunjung Taman Tabebuya. STRING (Satuan Tulisan Riset dan Inovasi Teknologi), 2(3): 299–307.

Darwis, D., Pratiwi, E.S. & Pasaribu, A.F.O. 2020. Penerapan Algoritma Svm Untuk Analisis Sentimen Pada Data Twitter Komisi Pemberantasan Korupsi Republik Indonesia. Edutic-Scientific Journal of Informatics Education, 7(1).

DHARMAWAN, F.Y. n.d. ANALISIS JAWABAN SOAL ESSAY MENGGUNAKAN TEXT MINING DENGAN METODE NAÏVE BAYES.

Dougherty, G. 2012. Pattern recognition and classification: an introduction. Springer Science & Business Media.

Farki, A. 2016. Pengaruh online customer review dan rating terhadap kepercayaan dan minat pembelian pada online marketplace di Indonesia.

Firdaus, D. 2017. Penggunaan Data Mining dalam Kegiatan Sistem Pembelajaran Berbantuan Komputer. Format, 6(2): 91–97.

Gunawan, B., Sastypratiwi, H. & Pratama, E.E. 2018. Sistem Analisis Sentimen pada Ulasan Produk Menggunakan Metode Naive Bayes. JEPIN (Jurnal Edukasi dan Penelitian Informatika), 4(2): 113–118.

Handayani, F. & Pribadi, F.S. 2015. Implementasi algoritma naive bayes classifier dalam pengklasifikasian teks otomatis pengaduan dan pelaporan masyarakat melalui layanan call center 110. Jurnal Teknik Elektro, 7(1): 19–24.

Hidayat, A.N. 2015. Analisis Sentimen Terhadap Wacana Politik Pada Media Masa Online Menggunakan Algoritma Support Vector Machine Dan Naive Bayes. Jurnal Elektronik Sistem Informasi dan Komputer, 1(1): 12–18.

HR, R.T., Wardoyo, A.E. & Pratama, M.R. n.d. Analisis Sentimen pada Twitter terhadap Kinerja Komisi Pemberantasan Korupsi (KPK) di Indonesia dengan Metode Naive Bayes.

Ipmawati, J. 2016. Komparasi teknik klasifikasi teks mining pada analisis sentimen. IJNS-Indonesian Journal on Networking and Security, 6(1).

Kim, W.G. & Park, S.A. 2017. Social media review rating versus traditional customer satisfaction. International Journal of Contemporary Hospitality Management.

Kotler, P., Keller, K.L. & Manceau, D. 2016. Marketing Management, 15e édition. New Jersy: Pearson Education.

Lubis, C.P., Rosnelly, R., Roslina, R., Situmorang, Z. & Wanayumini, W. 2021. Penerapan Metode Naïve Bayes dan C4. 5 Pada Penerimaan Pegawai di Universitas Potensi Utama. CSRID (Computer Science Research and Its Development Journal), 12(1): 51–63.

Mahmoud, M.A., Ahmad, M.S., Yusoff, M.Z.M. & Mustapha, A. 2015. Context identification of scientific papers via agent-based model for text mining (ABM-TM). New Trends in Computational Collective Intelligence. Springer, hal.51–61.

Muhson, A. 2010. Pengembangan media pembelajaran berbasis teknologi informasi. Jurnal Pendidikan Akuntansi Indonesia, 8(2).

Nisah, A. 2021. ANALISIS PERBANDINGAN PENDAPATAN ANTARA PEBISNIS ONLINE SHOP DENGAN UPAH MINIMUM KOTA (STUDI KASUS DI KOTA MAKASSAR). Economics Bosowa, 6(004): 38–50.

Nooraeni, R., Safiruddin, A.B., Afifah, A.F., Agung, K.D. & Rosyad, N.N. 2020. Analisis Sentimen Publik terhadap Sistem Zonasi Sekolah Menggunakan Data Twitter dengan Metode Naïve Bayes Classification. Faktor Exacta, 12(4): 315–322.

Norwawi, N.M. 2020. Recognition decision-making model using temporal data mining technique. Journal of Information and Communication Technology, 4: 37–56.

Octaviani, P.A., Wilandari, Y. & Ispriyanti, D. 2014. Penerapan Metode Klasifikasi Support Vector Machine (SVM) Pada Data Akreditasi Sekolah Dasar (SD) Di Kabupaten Magelang. Jurnal Gaussian, 3(4): 811–820.

Rahutomo, F., Saputra, P.Y. & Fidyawan, M.A. 2018. Implementasi Twitter Sentiment Analysis Untuk Review Film Menggunakan Algoritma Support Vector Machine. Jurnal Informatika Polinema, 4(2): 93.

Rasheed, M.M., Faieq, A.K. & Hashim, A.A. 2020. Android Botnet Detection Using Machine Learning. Ingénierie des Systèmes d’Information, 25(1).

Sarifudin, S. & Amelia, R.R. 2020. E-COMMERCE PADA ELLISA BAGS. JURNAL SINKOM Sistem Informasi, Informatika dan Komputer, 1(1): 26–34.

Sitepu, A.C., Wanayumini, W. & Situmorang, Z. 2021. Analisis Kinerja Support Vector Machine dalam Mengidentifikasi Komentar Perundungan pada Jejaring Sosial. JURNAL MEDIA INFORMATIKA BUDIDARMA, 5(2): 475–484.

Supradono, B. & Hanum, A.N. 2011. Peran Sosial Media Untuk Manajemen Hubungan dengan Pelanggan Pada Layanan E-Commerce. Value Added| Majalah Ekonomi dan Bisnis, 7(2).

Vimala, S. & Sharmili, K.C. 2018. Prediction of loan risk using naive bayes and support vector machine. Int Conf Adv Comput Technol (ICACT). hal.110–113.

Wu, X. & Kumar, V. 2009. The top ten algorithms in data mining. CRC press.