Perbandingan Klasifikasi Label Tunggal untuk Soal Ujian Fisika menggunakan Naive Bayes dan K-Fold Cross Validation

Herijanto, Christopher Kevin and Wahyuningsih, Yulia (2024) Perbandingan Klasifikasi Label Tunggal untuk Soal Ujian Fisika menggunakan Naive Bayes dan K-Fold Cross Validation. Jurnal Teknologi Terpadu, 10 (1). pp. 40-45. ISSN 2477-0043 ONLINE: 2460-7908

	Text arahmah,+06-1210-Perbandingan+Klasifikasi+Label+Tunggal+untuk+Soal+Ujian+Fisika+menggunakan (2).pdf Download (370kB)
	Text HASIL SIMILARITY-Perbandingan Klasifikasi Label Tunggal untuk Soal Ujian Fisika menggunakan Naive Bayes dan K-Fold Cross Validation.pdf Download (2MB)

Abstract

This research evaluates the use of the Naïve Bayes algorithm in classifying Physics questions with single labels. The main objective is to identify the best algorithm for classifying Physics questions to assist high school students with difficulty understanding them. The research method involves using a dataset containing Physics questions that need to be classified to facilitate learning for high school students. The Naïve Bayes algorithm is implemented using Google Colab to train the classification model using features extracted from the text of the Physics questions. Additionally, several other classification algorithms, such as Support Vector Machine (SVM), Logistic Regression, Decision Tree, and Random Forest, are tested, and their performance is compared. Experimental results show that Naïve Bayes provides competitive results in classifying singlelabel Physics questions. However, there are significant performance differences between Naïve Bayes and other algorithms, depending on the type and complexity of the classified Physics problems. In this study, SVM achieved higher accuracy, but Naïve Bayes excelled in training time. This research provides a deeper understanding of the strengths and weaknesses of Naïve Bayes in solving the task of classifying single-label Physics problems. These findings guide the development of more accurate classification models for application in the context of Physics learning.

Item Type:	Article
Uncontrolled Keywords:	Fisika, Klasifikasi Label Tunggal, Naive Bayes, Pembelajaran Mesin, Random Forest
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Teknik > Prodi Ilmu Informatika
Depositing User:	Yulia Wahyuningsih
Date Deposited:	01 Oct 2025 04:40
Last Modified:	01 Oct 2025 04:40
URI:	http://repositori.ukdc.ac.id/id/eprint/2476

Actions (login required)

View Item