PERBANDINGAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE DALAM KLASIFIKASI PERCERAIAN DI LABUHANBATU

MHD. SAHDANI RAFLI HASIBUAN, NPM 2209100079 (2026) PERBANDINGAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE DALAM KLASIFIKASI PERCERAIAN DI LABUHANBATU. Skripsi thesis, Universitas Labuhanbatu.

	Text COVER.pdf Download (561kB)
	Text BAB I.pdf Download (375kB)
	Text BAB II.pdf Download (454kB)
	Text BAB III.pdf Download (653kB)
	Text BAB IV.pdf Download (743kB)
	Text BAB V.pdf Download (174kB)
	Text DAFTAR PUSTAKA.pdf Download (218kB)
	Text LAMPIRAN.pdf Download (388kB)

Abstract

Penelitian ini bertujuan untuk membandingkan performa algoritma Naïve Bayes dan Support Vector Machine (SVM) dalam mengklasifikasikan perceraian di Kabupaten Labuhanbatu. Perceraian dipengaruhi oleh berbagai faktor seperti ekonomi, narkoba, judi, kekerasan dalam rumah tangga (KDRT), selingkuh, dan komunikasi, sehingga diperlukan pendekatan berbasis data untuk mengidentifikasi faktor dominan secara akurat. Metode penelitian menggunakan pendekatan kuantitatif dengan teknik machine learning. Data diperoleh dari Pengadilan Agama Labuhanbatu dan diolah melalui tahap preprocessing, pembagian data, pelatihan model, serta evaluasi menggunakan metrik akurasi, precision, recall, dan F1-score dengan aplikasi Orange Data Mining. Hasil penelitian menunjukkan bahwa Naïve Bayes memperoleh akurasi 95,4%, sedangkan SVM sebesar 96,4%. Selain itu, faktor KDRT merupakan faktor paling dominan dalam perceraian berdasarkan analisis Gain Ratio. Kesimpulannya, algoritma SVM memiliki performa yang lebih baik dibandingkan Naïve Bayes dalam klasifikasi perceraian. Kata kunci : Perceraian, Machine Learning, Naïve Bayes, SVM ================================================================================================ This study aims to compare the performance of Naïve Bayes and Support Vector Machine (SVM) algorithms in classifying divorce cases in Labuhanbatu Regency. Divorce is influenced by factors such as economic issues, drug abuse, gambling, domestic violence, infidelity, and communication problems, requiring a data-driven approach to identify dominant factors accurately. This research uses a quantitative approach with machine learning techniques. Data were obtained from the Religious Court of Labuhanbatu and processed through preprocessing, data splitting, model training, and evaluation using accuracy, precision, recall, and F1 score metrics with Orange Data Mining. The results show that Naïve Bayes achieved an accuracy of 95.4%, while SVM achieved 96.4%. Domestic violence was identified as the most dominant factor based on Gain Ratio analysis. In conclusion, SVM performs better than Naïve Bayes in classifying divorce cases. Keywords : Divorce, Machine Learning, Naïve Bayes, SVM

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Perceraian, Machine Learning, Naïve Bayes, SVM ============================================== Divorce, Machine Learning, Naïve Bayes, SVM
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > Sistem Informasi
Depositing User:	Unnamed user with email repository@ulb.ac.id
Date Deposited:	29 Apr 2026 03:26
Last Modified:	29 Apr 2026 03:27
URI:	http://repository.ulb.ac.id/id/eprint/2190

Actions (login required)

View Item