KLASIFIKASI AL – QUR’AN TERJEMAHAN BAHASA INDONESIA DENGAN MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM)
DOI:
https://doi.org/10.30996/konv.v18i1.6912Keywords:
Al-Qur’an, Teknik feature selection, Algoritma Support Vector Machine (SVM), AUC, f1-scoreAbstract
The classification of verses of the Koran in Indonesian translation aims to classify verses of the Koran that have the same meaning on certain topics. In this study, the labeling of translated Qur'anic verses is grouped into 6 categories including education, motivation, social, history, politics and science (mathematics). The method proposed in this study uses Chi Square feature selection and Principal Analysis with the application of a classification model using the Support Vector Machine (SVM) algorithm to group the translated verses of the Koran into 6 categories. The initial stage is preprocessing, which aims to find the weighting value for each document using TF-IDF. After getting the weighting value for each document, a search for the best classification model is carried out to label the verses of the Qur'an by using feature selection and without using feature selection. In this study, the best classification model results without using feature selection in the SVM algorithm, the AUC value is 83.3%, while using Chi Square feature selection, the AUC is 73.3%, while the PCA feature selection is 63.3%. So that this research is the best model in classifying the Indonesian translation of the Qur'anic verses without using feature selection with the highest AUC value of 83.3%.
Keywords: Feature Selection Techniques; Holy Qur’an; Algorithm Support Vector Machine (SVM); AUC; f1-score.
ABSTRAK
Klasifikasi ayat al-qur’an terjemahan Bahasa Indonesia bertujuan untuk mengelompokkan ayat alqur’an yang mempunyai makna yang sama pada topik tertentu. Pada penelitian ini pelabelan dokumen ayat al - qur’an terjemahan dikelompokkan menjadi 6 kategori diantaranya pendidikan, motivasi, sosial, sejarah, politik dan sains (matematika). Metode yang diusulkan dalam penelitian ini menggunakan feature selection Chi Square dan Principal Component Analysist (PCA) dengan penerapan model klasifikasi menggunakan algoritma Support Vector Machine (SVM) untuk mengelompokkan ayat al - qur’an terjemahan ke dalam 6 kategori. Tahap awal yang dilakukan adalah preprocessing bertujuan untuk mencari nilai pembobotan pada setiap dokumen dengan menggunakan TF-IDF. Setelah mendapatkan nilai pembobotan pada setiap dokumen dilakukan pencarian model klasifikasi terbaik untuk melabeli ayat al-qur’an dengan menggunakan feature selection dan tanpa menggunakan feature selection. Pada penelitian ini didapatkan hasil model klasifikasi terbaik tanpa menggunakan feature selection pada algoritma SVM didapatkan nilai AUC 83.3% sedangan dengan menggunakan feature selection Chi Square mendapatkan nilai AUC 73.3 % sedangkan dengan pada feature selection PCA mendapatkan nilai AUC 63.3 %. Sehingga penelitian ini model yang terbaik dalam mengklasifikasi ayat al-qur’an terjemahan Bahasa Indonesia tanpa menggunakan feature selection dengan nilai AUC tertinggi 83.3 %.
Kata Kunci: Teknik feature selection; Al-Qur’an; Algoritma Support Vector Machine (SVM); AUC; f1-score
Downloads
Downloads
Published
Issue
Section
License
Authors whose manuscript is published will approve the following provisions:
- The right to publication of all journal material published on the Konvergensi Teknologi Informasi & Komunikasi website is held by the editorial board with the author's knowledge (moral rights remain the property of the author).
- The formal legal provisions for access to digital articles of this electronic journal are subject to the terms of the Creative Commons Attribution-ShareAlike (CC BY-SA) license, which means Konvergensi Teknologi Informasi & Komunikasi reserves the right to store, modify the format, administer in database, maintain and publish articles without requesting permission from the Author as long as it keeps the Author's name as the owner of Copyright.
- Printed and electronic published manuscripts are open access for educational, research and library purposes. In addition to these objectives, the editorial board shall not be liable for violations of copyright law.

