Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Zahlul Fasya
Universitas Malikussaleh
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
ANALISIS SENTIMEN ULASAN MASYARAKAT TERHADAP APLIKASI SIREKAP 2024 PADA GOOGLE PLAY STORE MENGGUNAKAN METODE K-NEAREST NEIGHBORS (KNN) Zahlul Fasya; Muhammad Daud; Lidya Rosnita
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6612

Abstract

In the last general election, the Sirekap application experienced a series of failures that resulted in delays and inaccuracies in the delivery of election results data. This study aims to analyze and classify public sentiment towards the application. The method used is K-Nearest Neighbors (KNN) utilizing 21,593 reviews from the Google Play Store. The research stages included data collection and text pre-processing in the form of cleaning, tokenizing, normalization, stopword removal, and stemming. Sentiment labeling was performed automatically using a weighted lexicon method to divide the data into two classes, namely positive and negative. Features were extracted using TF-IDF, and the model was evaluated with 10-fold cross-validation before being tested using a ratio of 70% training data and 30% test data. The results showed extreme class imbalance, with negative sentiment dominating 90.1% of the dataset. This causes a significant performance disparity: the model achieves a recall of 98.31% for the negative class but only 50.79% for the positive class. These findings indicate that although KNN is effective for majority patterns, the model experiences prediction bias towards the minority class. As a final implementation, an interactive web application was created to demonstrate the model and display visualizations of the research results.  
Co-Authors Lidya Rosnita Muhammad Daud