Analisis Sentimen Review Pembelian Produk Di Marketplace Shopee Menggunakan Pendekatan Natural Language Processing

Yuvensius Bala Lado
Elfira Umar
Katarina Yunita

Journal Of Informatics And Busisnes
Vol. 2 No. 3 (2024): Oktober - Desember

Abstract This study analyzes product reviews in the market, focusing on the "Kaos Oversize" product, to classify them into positive and negative reviews. The research aims to demonstrate the effectiveness of using K-Nearest Neighbors (KNN) and Term Frequency-Inverse Document Frequency (TF-IDF) algorithms with Natural Language Processing (NLP) approach in classifying product reviews. The study found that the NLP method achieved a higher accuracy, precision, and recall rate compared to not using NLP. The results suggest that analyzing keywords in reviews can represent the overall opinion of the buyers towards the product, which can be useful information for retailers to evaluate their products and services.