PERBANDINGAN ALGORITMA NAÏVE BAYES CLASSIFIER DAN SUPPORT VECTOR MACHINE DENGAN MENGANALISIS SENTIMEN ULASAN PELANGGAN SHOPEE INDONESIA
Abstract
Perkembangan teknologi dan meningkatnya penggunaan e-commerce di Indonesia mendorong masyarakat untuk aktif memberikan ulasan terhadap layanan maupun produk. Shopee menjadi salah satu platform yang banyak memperoleh sorotan publik, khususnya melalui media sosial Twitter. Penelitian ini bertujuan membandingkan performa dua algoritma klasifikasi teks populer, yaitu Naïve Bayes Classifier dan Support Vector Machine (SVM), dalam menganalisis sentimen ulasan pelanggan Shopee. Tahapan penelitian mencakup pengumpulan data melalui crawling, preprocessing teks (cleaning, tokenizing, stopword removal, dan stemming), serta representasi teks ke dalam bentuk vektor fitur menggunakan metode TF-IDF. Data kemudian dibagi menjadi data latih dan data uji untuk diklasifikasikan dengan kedua algoritma. Hasil penelitian menunjukkan bahwa SVM memiliki performa lebih baik dibandingkan Naïve Bayes. Melalui uji cross-validation, SVM mencapai rata-rata akurasi 74,66%, sedangkan Naïve Bayes hanya 67,21%. Selain itu, evaluasi menggunakan confusion matrix memperlihatkan SVM memiliki nilai F1-score lebih seimbang pada kedua kelas sentimen (positif dan negatif), sementara Naïve Bayes cenderung bias pada kelas positif. Dengan demikian, penelitian ini menyimpulkan bahwa SVM lebih efektif untuk klasifikasi sentimen ulasan pelanggan Shopee, terutama pada data yang tidak seimbang. Hasil penelitian ini diharapkan menjadi referensi dalam pengembangan sistem analisis opini publik dan strategi peningkatan layanan e-commerce.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ali Muhammad Najib, Amin Hidayat

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Prosiding Seminar Informatika dan Sistem Informasi have CC-BY-NC-SA or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities, Prosiding Seminar Informatika dan Sistem Informasi recognize that free access is better than priced access, libre access is better than free access, and libre under CC-BY-NC-SA or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
Prosiding Seminar Informatika dan Sistem Informasi is licensed under a Creative Commons Attribution 4.0 International License
YOU ARE FREE TO:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms