The Shopee Application User Reviews Sentiment Analysis Employing Naïve Bayes Algorithm

Abstract

With the significant growth of internet use in Indonesia, there has been a surge in online business activity. The convenience offered by online platforms is increasingly in demand because it allows consumers to shop without being bound by a certain time or location. Before making a purchase, consumers tend to look for information first through various sources such as reviews on blogs, Instagram, TikTok, or reviews on the YouTube platform which is integrated in the application. This research adopted a method that included planning, literature study, data collection, and data processing using a dataset from the Play Store application which was taken using the Python library with an initial amount of 5000 data. After a manual filtering process which involved removing slang words, eliminating duplications, and normalizing punctuation marks, the remaining data was 3946. The application of the Naïve Bayes algorithm in this research uses probability methods to classify and predict 3141 training data and 805 test data, with Python library help. The accuracy calculation results show satisfactory performance, with an accuracy of 86.00%, precision of 80.74%, recall of 78.13%, and f1-score of 79.00% on a dataset of 3946. Analysis from this research shows the dominance of positive sentiment in 2050 data, while sentiment negative amounted to 1199 data. The amount and quality of training data plays an important role in system predictions, where high data quality provides better accuracy in predicting sentiment classes

Classification of Hoax News Using the Naïve Bayes Method

“…Experimental results highlight the superiority of Naïve Bayes in some fake news detection [4]. Apart from that, recent research has also expanded the application of the Naïve Bayes algorithm to other fields, such as sentiment analysis of application user reviews, as carried out by Pasaribu & Sriani (2023) [5]. Related research highlights essential developments in using Naïve Bayes algorithms in fake news detection and classification.…”

“…This research is ardently dedicated to confronting this multifaceted challenge by strategically implementing a robust and state-of-the-art classification system meticulously designed to discern and identify hoax news circulating through the intricate web of internet media channels. At the core of this classification process lies a meticulous preprocessing stage, and among the classification algorithms utilized, Naïve Bayes stands out for its simplicity and high accuracy [5] [6].…”

Analisis Sentimen Film Dirty Vote Menggunakan BERT (Bidirectional Encoder Representations from Transformers)

“…Peneliti memanfaatkan Google Colab sebagai platform untuk melakukan proses pengolahan data dan pelatihan model [29]. Google Colab merupakan layanan komputasi awan berbasis web yang memungkinkan Peneliti menjalankan kode Python dan mengakses sumber daya komputasi GPU secara gratis [30] [31]. Dengan menggunakan Google Colab, Peneliti dapat mengimplementasikan dan menjalankan skrip Python untuk melakukan tokenisasi, pembersihan data, serta pelatihan model BERT dengan mudah.…”

Analisa Online Customer Review (OCR) Menggunakan Algoritma Naive Bayes berbasis Particial Swarm Optimization (PSO)

“…Ulasan pelanggan online merupakan umpan balik yang diberikan oleh konsumen mengenai evaluasi produk yang mencakup berbagai aspek. Informasi ini memungkinkan konsumen untuk menilai kualitas produk berdasarkan pengalaman yang dibagikan oleh orang lain yang telah membeli dari penjual online yang sama (Pasaribu & Sriani, 2023). Online Customer Review dan Online Customer Rating, memiliki dampak signifikan pada keputusan pembelian di marketplace Shopee karena ketika orang memutuskan untuk membeli sesuatu di Shopee, mereka mempertimbangkan berapa biayanya, apa yang dikatakan pelanggan lain tentang produk tersebut, dan peringkat yang telah diterimanya (Nurmaningsih, 2023).…”

“…Metode Naïve Bayes merupakan metode klasifikasi dalam machine learning yang unggul dalam menggunakan sampel data pelatihan untuk memperkirakan parameter yang terlibat dalam proses klasifikasi dengan cepat dan menghasilkan akurasi yang tinggi (Pasaribu & Sriani, 2023). Menggunakan algoritma Naïve Bayes dalam melakukan sentimen analisis dalam ulasan pengguna, memungkinkan ekstraksi otomatis informasi penting dari volume teks yang besar, memfasilitasi penentuan kualitas produk yang objektif dan meningkatkan manajemen kepuasan pelanggan untuk platform e-commerce (Laia & Yamin, 2023) Particle Swarm Optimization (PSO) adalah teknik optimasi yang sangat sederhana untuk menerapkan dan memvariasikan beberapa parameter (Putra et al, 2023).…”