Ertha, Therecia (2025) Analisis Faktor-Faktor yang Memengaruhi Jenis Perceraian di Jakarta Timur pada Masa Pandemi Covid-19 Menggunakan Metode Regresi Logistik Biner dengan Pendekatan SMOTE-NC. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003211111-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003211111-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (7MB) | Request a copy |
Abstract
Perceraian adalah berakhirnya ikatan perkawinan secara hukum yang terjadi akibat ketidakharmonisan dalam rumah tangga, dimana pasangan suami istri tidak lagi dapat menjalankan hak dan kewajibannya dengan baik. Dalam hukum Islam, perceraian terbagi menjadi cerai talak yaitu cerai yang diajukan oleh suami dan cerai gugat yaitu cerai yang diajukan oleh istri melalui pengadilan agama. Selama masa pandemi Covid-19 tahun 2021, angka perceraian di Indonesia melonjak signifikan, mencapai 447.743 kasus. Provinsi DKI Jakarta menempati urutan ke lima tingkat perceraian nasional, dengan Jakarta Timur sebagai wilayah tertinggi, yaitu sebesar 4.765 perkara yang terdiri atas 74% cerai gugat dan 26% cerai talak, ini mencerminkan meningkatnya kesadaran gender. Penelitian ini bertujuan untuk menganalisis faktor-faktor yang memengaruhi jenis perceraian di Jakarta Timur selama pandemi Covid-19 dengan menggunakan metode regresi logistik biner. Penanganan ketidakseimbangan data dilakukan melalui pendekatan SMOTE-NC, dengan lima variasi komposisi hingga diperoleh model terbaik pada proporsi 50:50 untuk kedua jenis perceraian. Hasil penelitian menunjukkan bahwa model tersebut memiliki performa klasifikasi terbaik dengan akurasi 67,41%, sensitivitas 71,16%, spesifisitas 63,67%, dan AUC sebesar 73,94%. Variabel yang berpengaruh signifikan meliputi Usia Pernikahan (X1), Usia Penggugat Saat Menikah (X2), Usia Tergugat Saat Menikah (X3), Pekerjaan Penggugat (X4), Pekerjaan Tergugat (X5), Tingkat Pendidikan Penggugat (X6), Tingkat Pendidikan Tergugat (X7), Kepemilikan Anak (X8), serta Penyebab Perceraian (X9). Temuan ini menunjukkan bahwa faktor sosial, ekonomi, demografi dan psikologis memengaruhi kecenderungan jenis perceraian, serta pendekatan SMOTE-NC efektif dalam menghasilkan model prediktif yang andal pada data tidak seimbang.
=========================================================================================================================================
Divorce is the legal end of a marriage that happens when a couple can no longer maintain harmony in their household and are unable to fulfill their rights and responsibilities properly. In Islamic law, divorce is classified into cerai talak, which is initiated by the husband, and cerai gugat, which is initiated by the wife through the religious court. During the Covid-19 pandemic in 2021, the number of divorce cases in Indonesia increased significantly, reaching a total of 447,743. The Special Capital Region of Jakarta ranked fifth in national divorces cases, with East Jakarta recording the highest number of cases within the province, amounting to 4,765 cases—of which 74% were cerai gugat and 26% were cerai talak. This reflects a growing awareness of gender roles within households. This study aims to find out the factors that affect the type of divorce in East Jakarta during the Covid-19 pandemic using the binary logistic regression method. To fix the imbalanced data, the SMOTE-NC (Synthetic Minority Over-sampling Technique for Nominal and Continuous) method was applied, generating five variations in class proportion, and the best model was achieved with a 50:50 balance between the two divorce types. The final model showed good classification performance with an accuracy of 67.37%, sensitivity of 71.21%, specificity of 63.53%, and AUC of 73.86%. Significant predictors included duration of marriage, age at marriage of both parties, type of occupation, educational level, presence of children, and reasons for divorce. The findings indicate that social, economic, demography, and psychological factors contribute significantly to divorce type, and that the SMOTE-NC method is effective for improving predictive modeling on imbalanced datasets.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Pandemi Covid-19, Perceraian, Regresi Logistik Biner, SMOTE-NC,Binary Logistic Regression, Covid-19 Pandemic, Divorce, SMOTE-NC. |
| Subjects: | H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HA Statistics > HA31.7 Estimation H Social Sciences > HQ The family. Marriage. Woman Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Therecia Ertha |
| Date Deposited: | 01 Aug 2025 06:25 |
| Last Modified: | 01 Aug 2025 06:25 |
| URI: | http://repository.its.ac.id/id/eprint/125531 |
Actions (login required)
 |
View Item |