NUGRAHA, AGUNG (2023) Analisis Pengelompokan Teks Pada Data Pengaduan Masyarakat Menggunakan Algoritma K-Means Periode 20212022 (studi kasus: Dinas Sosial DKI Jakarta). S1 thesis, Universitas Mercu Buana Bekasi.
|
Text
41519210014 - Agung Nugraha - 01 Cover.pdf Download (1MB) | Preview |
|
|
Text
41519210014 - Agung Nugraha - 02 Abstrak.pdf Download (33kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text
41519210014 - Agung Nugraha - 03 BAB 1.pdf Restricted to Registered users only Download (159kB) |
|
|
Text
41519210014 - Agung Nugraha - 04 BAB 2.pdf Restricted to Registered users only Download (131kB) |
|
|
Text
41519210014 - Agung Nugraha - 05 BAB 3.pdf Restricted to Registered users only Download (319kB) |
|
|
Text
41519210014 - Agung Nugraha - 06 BAB 4.pdf Restricted to Registered users only Download (615kB) |
|
|
Text
41519210014 - Agung Nugraha - 07 BAB 5.pdf Restricted to Registered users only Download (72kB) |
|
|
Text
41519210014 - Agung Nugraha - 08 Daftar Pustaka.pdf Restricted to Registered users only Download (83kB) |
|
|
Text
41519210014 - Agung Nugraha - 09 Lampiran.pdf Restricted to Registered users only Download (1MB) |
Abstract
Indonesia memiliki banyak sarana akses untuk memudahkan masyarakat dalam mencari dan berbagi informasi tentang peristiwa-peristiwa yang terjadi dalam kehidupan sehari-hari serta memperoleh banyak informasi dari laporan pengaduan masyarakat. pada penelitian ini, penulis melakukan implementasi dan pengelompokkan teks dengan menerapkan metode data mining terhadap data laporan pengaduan dari website https://dinsos.jakarta.go.id melalui aplikasi SITAJIR (Sistem Informasi Tanya Jawab Interaktif) untuk mencari dan mengklasifikasikan topik Laporan pengaduan yang paling sering dilaporkan dengan algoritma k-means. Pengelompokan tersebut dapat dibagi menjadi 5 Cluster menggunakan Elbow Method yaitu Cluster 1 DTKS (Data Terpadu Kesejahteraan Sosial), Cluster 2 yaitu KLJ (Kartu Lansia Jakarta), Cluster 3 yaitu KAJ (Kartu Anak Jakarta) dan KJP (Kartu Jakarta Pintar), Cluster 4 yaitu BPJS (Badan Penyelenggara Jaminan Sosial) dan Cluster 5 yaitu merupakan pertanyaan mengenai banyaknya jenis-jenis bantuan sosial lainnya yang sering diadakan. Kata Kunci : Data Mining, Clustering, K-Means, Pengaduan. Indonesia has many means of access to make it easier for the public to find and share information about events that occur in daily life and obtain a lot of information from reports of public complaints. In this study, the authors carried out the implementation and grouping of texts by applying the data mining method to complaint report data from the website https://dinsos.jakarta.go.id through the SITAJIR (Interactive Question and Answer Information System) application to find and classify the most frequently reported complaint report topics with k-means algorithm. The grouping can be divided into 5 Clusters using the Elbow Method, namely cluster 1 DTKS (Integrated Social Welfare Data), Cluster 2 namely KLJ (Jakarta Elderly Card), Cluster 3 namely KAJ (Jakarta Child Card) and KJP (Jakarta Smart Card), Cluster 4 namely BPJS (Social Security Organizing Agency) and Cluster 5 which is a question about the many other types of social assistance that are often held. Keywords: Data Mining, Clustering, K-Means, Complaints.
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO 23 025 |
| NIM/NIDN Creators: | 41519210014 |
| Uncontrolled Keywords: | Data Mining, Clustering, K-Means, Pengaduan. |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | siti maisyaroh |
| Date Deposited: | 27 Sep 2023 03:48 |
| Last Modified: | 27 Sep 2023 03:48 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/81509 |
Actions (login required)
 |
View Item |
