ENITA, FRISKA DWI (2023) PEMODELAN EKSTRAKSI INFORMASI PADA LAPORAN HASIL PENGAWASAN INTERN PEMERINTAH. Skripsi thesis, Politeknik Keuangan Negara STAN.
|
Text (Cover)
01.Cover_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (407kB) |
|
|
Text (Abstrak)
02.Abstrak_Fahmy Rizki Zakaria_4132210016.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (149kB) |
|
|
Text (Daftar isi)
03.Daftar Isi_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (234kB) |
|
|
Text (BAB I)
Bab I_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (341kB) |
|
|
Text (BAB II)
Bab II_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (362kB) |
|
|
Text (BAB III)
Bab III_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (208kB) |
|
|
Text (BAB IV)
Bab IV_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (699kB) |
|
|
Text (BAB V)
Bab V_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (208kB) |
|
|
Text (Daftar pustaka)
Daftar Pustaka_Friska Dwi Enita_4132210013.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (209kB) |
Abstract
Skripsi ini membahas proses text mining yang dapat mempermudah auditor pada Badan Pengawasan Keuangan dan Pembangunan dalam mengompilasi isi dokumen laporan hasil pengawasan secara efektif. Tujuan penelitian adalah untuk menghasilkan model text mining yang dapat mempermudah auditor dalam mengompilasi isi dokumen laporan hasil pengawasan secara efektif dengan cara ekstraksi data teks. Metodologi penelitian yang digunakan adalah Knowledge Discovery in Databases (KDD) yang meliputi beberapa tahapan yaitu pemilihan data, pra-pemrosesan data, transformasi data, penambangan data, dan evaluasi. Hasil penelitian menunjukkan bahwa text mining dapat digunakan untuk mengompilasi isi dokumen laporan hasil pengawasan dengan efektif, yang dibuktikan lewat proses text mining atas 10 dokumen laporan hasil pengawasan SPIP dengan mayoritas hasil ekstraksi sesuai dengan teks di dalam dokumen. Beberapa hal yang menyebabkan ketidaksesuaian antara hasil ekstraksi dengan teks di dalam dokumen adalah perbedaan format penulisan pada tiap laporan, double spasi pada dokumen, penulisan kata yang disingkat, dan format laporan yang tidak diisi atau sengaja dikosongkan. Kata kunci: text mining, ekstraksi informasi, laporan hasil pengawasan, audit. This thesis discusses the text mining process that can facilitate auditors at the Financial and Development Supervisory Agency (Badan Pengawasan Keuangan dan Pembangunan) in compiling the contents of supervision report documents effectively. The research objective is to produce a text mining model that can assist auditors in effectively compiling the contents of supervision report documents by extracting text data. The research methodology used is Knowledge Discovery in Databases (KDD), which includes several stages: data selection, data preprocessing, data transformation, data mining, and evaluation. The research results show that text mining can be used to compile the contents of supervision report documents effectively, as evidenced by the text mining process on 10 SPIP supervision report documents, with the majority of the extraction results matching the text within the documents. Some factors causing discrepancies between the extraction results and the text within the documents include differences in writing formats in each report, double spacing in documents, abbreviated word usage, and empty or intentionally blank report formats. Keywords: text mining, information extraction, supervision report, audit.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Subjects: | PKN STAN Subject Area > Audit |
| Divisions: | 62303 Diploma IV Akuntansi Sektor Publik |
| Depositing User: | Perpustakaan PKN STAN |
| Date Deposited: | 05 Jan 2026 03:07 |
| Last Modified: | 05 Jan 2026 03:07 |
| URI: | http://eprints.pknstan.ac.id/id/eprint/3086 |
Actions (login required)
![]() |
View Item |

