Interpretasi hasil klasterisasi hadits shahih menggunakan variasi algoritma K-Means

Shidiq, Muhammad Faisal (2023) Interpretasi hasil klasterisasi hadits shahih menggunakan variasi algoritma K-Means. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_Cover.pdf

Download (75kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_Abstrak.pdf

Download (105kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
3_DaftarIsi.pdf

Download (57kB) | Preview
[img]
Preview
Text (BAB I)
4_Bab1.pdf

Download (211kB) | Preview
[img] Text (BAB II)
5_Bab2.pdf
Restricted to Registered users only

Download (386kB) | Request a copy
[img] Text (BAB III)
6_Bab3.pdf
Restricted to Registered users only

Download (381kB) | Request a copy
[img] Text (BAB IV)
7_Bab4.pdf
Restricted to Registered users only

Download (472kB) | Request a copy
[img] Text (BAB V)
8_Bab 5.pdf
Restricted to Registered users only

Download (50kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
9_daftarPustaka.pdf
Restricted to Registered users only

Download (181kB) | Request a copy

Abstract

INDONESIA : Hadits merupakan sumber hukum agama Islam kedua setelah Al-Qur'an, di dalam hadis banyak bab yang membahas beberapa kasus dan akan menarik untuk dipadukan dengan teknik data mining khususnya klasterisasi untuk mengelompokkan hadis ke dalam beberapa kelompok berdasarkan Matan (isi hadits) secara otomatis. Clustering merupakan teknik pengelompokan data berdasarkan kriteria data, dalam clustering memiliki beberapa metode diantaranya K-Means. Penelitian ini akan mencoba mengelompokkan teks Hadits terjemahan bahasa Indonesia menggunakan algoritma K-Means dengan beberapa parameter dan eksperimen yang ditentukan. Penelitian ini digunakan untuk mengetahui bagaimana dan seberapa akurat kinerja algoritma K-means dalam pengelompokan Hadits sehingga dapat dikatakan layak untuk digunakan di kehidupan sehari-hari atau tidak. Hasil penelitian ini menunjukkan bahwa beberapa parameter yang digunakan mempengaruhi hasil evaluasi cluster, terutama pada centroid 10 dan 15, selain itu pemilihan data dan kata dalam hadits juga sangat mempengaruhi hasil yang didapat. Pada perhitungan Confusion Matrix, K-means memiliki akurasi sebesar 87% pada 124 data latih dan menggunakan data uji sebanyak 31 data. Dengan hasil di atas menunjukkan bahwa kinerja dan tingkat akurasi metode K-means baik dalam pengelompokan teks hadits bahasa Indonesia. ENGLISH : Hadith is the second source of Islamic religious law after the Qur'an, in hadith there are many chapters that discuss several cases and it would be interesting to combine it with data mining techniques, especially clustering to group hadiths into groups based on Matan (hadith content) automatically. Clustering is a data grouping technique based on data criteria, in clustering there are several methods including K-Means. This study will try to classify Indonesian translation of Hadith texts using the K-Means algorithm with several parameters and experiments determined. This research is used to find out how and how accurately the K-means algorithm performs in grouping Hadith so that it can be said that it is feasible to use in everyday life or not. The results of this study indicate that several parameters used affect the results of cluster evaluation, especially at centroids 10 and 15, besides that the selection of data and words in the hadith also greatly influences the results obtained. In the Confusion Matrix calculation, K -means has an accuracy of 0.87 at 90% of the training data of 124 training data and uses 10% of the test data of 31 data. The results above show that the performance and accuracy of the K-means method are good in grouping Indonesian hadith texts.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Algoritma K-means; Clustering; Confusion Matrix; Data Mining; Hadits;
Subjects: Data Processing, Computer Science
Data Processing, Computer Science > Computer Science Education
Islam > Hadith
Numerical Analysis > Algorithms
Divisions: Fakultas Sains dan Teknologi > Program Studi Teknik Informatika
Depositing User: Muhammad Faisal Shidiq
Date Deposited: 22 Sep 2023 02:39
Last Modified: 22 Sep 2023 02:39
URI: https://digilib.uinsgd.ac.id/id/eprint/78792

Actions (login required)

View Item View Item