Perwira, Gema Adi (2022) Klasifikasi Berita Kriminalitas Dari Situs Berita Mainstream Untuk Pembangunan Petakabar Berdasarkan Tingkat Keparahan Menggunakan Metode Logistic Regression. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 05111840000138-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
05111840000138-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB) |
Abstract
Kriminalitas adalah suatu tindakan pelanggaran hukum dan norma-norma sosial serta agama yang menyerang fisik, ekonomi, psikologi serta mental yang melibatkan sedikit orang maupun banyak orang. Tingkatan kejahatan sendiri bermacam macam, dari kejahatan ringan sampai dengan kejahatan berat. Namun, apapun tingkatannya tetap saja merugikan bagi masyarakat sekitar bahkan merugikan negara. Pada Tugas Akhir ini, dilakukan penggalian informasi dari berita dengan topik kriminalitas yang terjadi di Indonesia. Yang dilakukan adalah dengan cara scraping berita kriminalitas melalui situs berita yaitu detik.com. Kemudian hasil scraping tersebut dilakukan penggalian informasi berupa 4W (What, Who, When, dan Where). Metode query expansion digunakan untuk penggalian informasi what, sedangkan metode Name Entity Recognition (NER) digunakan untuk penggalian informasi who, when, dan where. Setelah didapatkan semua informasi pada berita, dilakukan deteksi tingkat keparahan untuk melihat seberapa parah berita tersebut dengan menggunakan metode POS Tagging. Terakhir adalah klasifikasi tingkat keparahan berita menggunakan metode machine learning yaitu Logistic Regression. Hasil akurasi dari metode Logistic Regression berdasarkan evaluasi adalah 88%. Hasil Tugas Akhir ini adalah dataset yang berisi berita beserta informasi 4W dan tingkat keparahannya, yang kemudian dataset tersebut digunakan untuk pembuatan Petakabar yang menampilkan seluruh informasi berita terkait kriminalitas di Indonesia.
==============================================================================================================================
Crime is an act of violating the law and social and religious norms that attack physically, economically, psychologically and mentally involving a few people or many people. The level of crime itself varies, from minor crimes to serious crimes. However, whatever the level is, it is still detrimental to the surrounding community and even to the state. In this Final Project, information is extracted from the news on the topic of crime in Indonesia. What is done is by scraping crime news through a news site, namely detik.com. Then the results of the scraping carried out extracting information in the form of 4W (What, Who, When, and Where). The query expansion method is used to extract what information, while the Name Entity Recognition (NER) method is used to extract who, when, and where information. After getting all the information on the news, the severity level is detected to see how severe the news is using the POS Tagging method. The last is the classification of the severity of the news using the machine learning method, namely Logistic Regression. The result of the accuracy of the Logistic Regression method based on the evaluation is 88%. The result of this final project is a dataset that contains news along with 4W information and its severity, which is then used to make a news report that displays all news information related to crime in Indonesia.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSIf 001.012 Per k-1 2022 |
| Uncontrolled Keywords: | Kriminalitas, scraping, query expansion, NER, POS Tagging, Logistic Regression. Crime, scraping, query expansion, NER, POS Tagging, Logistic Regression. |
| Subjects: | H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects ) |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Mr. Marsudiyana - |
| Date Deposited: | 26 May 2026 04:26 |
| Last Modified: | 26 May 2026 04:26 |
| URI: | http://repository.its.ac.id/id/eprint/133437 |
Actions (login required)
 |
View Item |