Application Of K-Nearest Neighbor Algoritma for Customer Review Sentiment Analysis at Ngeboel Vapestore Shop

This study applies the K-Nearest Neighbor (K-NN) algorithm to classify customer sentiments from online reviews about Ngeboel Vapestore, a local MSME in the vape industry. A total of 175 reviews from Google Review and Instagram were processed using standard NLP techniques and TF-IDF for feature extr...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Aryanda, Ita Arfyanti, Yulindawati Yulindawati
Format: Article
Language:English
Published: LPPM STIKI Malang 2025-06-01
Series:J-Intech (Journal of Information and Technology)
Subjects:
Online Access:https://jurnal.stiki.ac.id/J-INTECH/article/view/1893
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study applies the K-Nearest Neighbor (K-NN) algorithm to classify customer sentiments from online reviews about Ngeboel Vapestore, a local MSME in the vape industry. A total of 175 reviews from Google Review and Instagram were processed using standard NLP techniques and TF-IDF for feature extraction. The best K-NN model (k=3) achieved 85.4% accuracy. Although Logistic Regression achieved higher accuracy (92.6%), it failed to detect negative sentiment. The findings highlight the potential and limitations of K-NN for sentiment analysis in underexplored MSME contexts like vape retail. The study recommends further model improvements and broader MSME applications.
ISSN:2303-1425
2580-720X