MIFTAH, Aiqohaki Mayasya and Waspada, Indra and Wibawa, Helmie Arif (2026) PEMODELAN PROFIL SANTRI MENGGUNAKAN HIERARCHICAL CLUSTERING DAN K-MEANS UNTUK STRATEGI PEMBINAAN DAN PEMETAAN PEMBELAJARAN ADAPTIF. Masters thesis, UNIVERSITAS DIPONEGORO.
|
Text
COVER-1 (1).pdf Download (97kB) |
|
|
Text
COVER.pdf Restricted to Repository staff only Download (4MB) |
|
|
Text
BAB I.pdf Download (1MB) |
|
|
Text
BAB II.pdf Download (14MB) |
|
|
Text
BAB III.pdf Restricted to Repository staff only Download (10MB) |
|
|
Text
BAB IV.pdf Restricted to Repository staff only Download (16MB) |
|
|
Text
BAB V.pdf Restricted to Repository staff only Download (869kB) |
|
|
Text
DAFTAR PUSTAKA.pdf Download (2MB) |
|
|
Text
LAMPIRAN.pdf Restricted to Repository staff only Download (2MB) |
Abstract
Keberagaman karakteristik santri memerlukan pendekatan berbasis data untuk menghasilkan profil yang dapat mendukung strategi pembinaan dan pemetaan pembelajaran adaptif. Penelitian ini bertujuan untuk mengidentifikasi profil santri berdasarkan kemiripan karakteristik menggunakan metode Hybrid Hierarchical Clustering–K-Means. Penelitian menggunakan data 178 santri dengan 11 variabel yang mencakup aspek karakter, gaya belajar, serta indikator pendukung lainnya. Proses clustering dilakukan menggunakan Agglomerative Hierarchical Clustering dengan metode Ward Linkage dan Euclidean Distance untuk membentuk struktur awal klaster, kemudian hasilnya digunakan sebagai inisialisasi centroid pada algoritma K-Means. Hasil penelitian menunjukkan bahwa model hybrid menghasilkan 3 profil utama santri dengan distribusi anggota masing-masing sebesar 91 santri (51,1%) sebagai Klaster 0 (Tertib tapi Kurang Jujur), 42 santri (23,6%) sebagai Klaster 1 (Jujur, Peduli, dan Berprestasi), dan 45 santri (25,3%) sebagai Klaster 2 (Jujur tapi Pendiam). Analisis karakteristik klaster menunjukkan adanya perbedaan pola antar kelompok terutama pada aspek capaian akademik, religius, dan kecenderungan pembelajaran. Hasil penelitian menunjukkan bahwa pendekatan Hybrid Hierarchical Clustering–K-Means mampu menghasilkan segmentasi profil santri secara objektif dan dapat digunakan sebagai dasar penyusunan strategi pembinaan yang lebih sesuai dengan karakteristik masing-masing kelompok.
Kata kunci : Hybrid Clustering, Hierarchical Clustering, K-Means, Profil Santri
The diversity of student characteristics requires a data-driven approach to generate student profiles that can support mentoring strategies and adaptive learning mapping. This study aims to identify student profiles based on characteristic similarities using the Hybrid Hierarchical Clustering–K-Means method. The study involved data from 178 students with 11 variables representing character traits, learning styles, and supporting indicators. The clustering process was performed using Agglomerative Hierarchical Clustering with Ward Linkage and Euclidean Distance to establish the initial cluster structure, followed by the use of clustering results as initial centroids for the K-Means algorithm. The results showed that the hybrid model successfully generated three main student profiles with cluster distributions of 91 students (51.1%) as Cluster 0 (Orderly but Low Honesty), 42 students (23.6%) as Cluster 1 (Honest, Caring, and High Achieving), and 45 students (25.3%) as Cluster 2 (Honest but Reserved). Cluster characterization revealed different patterns among groups, particularly in academic achievement, religious aspects, and learning tendencies. The results indicate that the Hybrid Hierarchical Clustering–K-Means approach is capable of producing objective student segmentation and can be utilized as a basis for developing mentoring strategies that are more appropriate according to the characteristics of each group.
Keywords : Hybrid Clustering, Hierarchical Clustering, K-Means, Student Profiling
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Hybrid Clustering, Hierarchical Clustering, K-Means, Profil Santri |
| Subjects: | Sciences and Mathemathic |
| Divisions: | Postgraduate Program > Master Program in Information System |
| Depositing User: | ekana listianawati |
| Date Deposited: | 18 Nov 2026 02:01 |
| Last Modified: | 18 Nov 2026 02:01 |
| URI: | https://eprints2.undip.ac.id/id/eprint/64399 |
Actions (login required)
![]() |
View Item |
