Claim Missing Document
Check
Articles

Found 1 Documents
Search

Analisis Sentimen Pada Ulasan Pengguna Platform E-commerce Menggunakan Algoritma K-Nearest Neighbor Tandiapa, Saron; Rorimpandey, Gladly Caren
The Indonesian Journal of Computer Science Vol. 15 No. 1 (2026): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v15i1.5050

Abstract

The development of e-commerce in Indonesia offers significant opportunities for MSMEs, yet the multitude of platform choices makes it difficult for them to determine the most suitable one. This study aims to analyze the user review sentiments toward five major e-commerce platforms (Shopee, Tokopedia, Lazada, Blibli, and Bukalapak) using the K-Nearest Neighbor (KNN) algorithm. A total of 5,995 reviews were collected from the Google Play Store via web scraping, then processed through pre-processing steps (such as case folding, tokenization, and stemming). Reviews were classified into positive, negative, and neutral sentiments using a lexicon-based approach, with Term Frequency-Inverse Document Frequency (TF-IDF) as the vectorization technique. The results show that Blibli has the highest KNN accuracy (64%), while the highest positive sentiment was achieved by Lazada with an F1-score of 54%. The research also developed a web-based application to help MSMEs analyze user sentiment across various e-commerce platforms.