Analisis Sentimen Aplikasi Sosial Media Bimbingan Belajar Online Menggunakan Metode K-Nearest Neighbors(KNN)

Zahro, Khairatuz (2025) Analisis Sentimen Aplikasi Sosial Media Bimbingan Belajar Online Menggunakan Metode K-Nearest Neighbors(KNN). Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (30kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (34kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (167kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

This study discusses sentiment analysis of user comments on the Pahamify application using the K-Nearest Neighbors (KNN) algorithm. A total of 1,200 Indonesian-language comments were collected, and after preprocessing, 1,173 labeled data (positive, negative, neutral) from expert annotation were obtained. The data was split into 80% for training and 20% for testing. The KNN model was trained to recognize sentiment patterns based on feature weighting using TF-IDF. To address class imbalance, the SMOTE method was applied, and Chi-Square testing was used for important feature selection. The model was tested using K values ranging from 1 to 18. The best result was achieved at K = 7, with an accuracy of 73% and the highest F1-Score of 80% in the positive class. These results indicate that the KNN model can effectively learn sentiment characteristics, particularly in recognizing positive sentiment.

Actions (login required)

View Item