Tirtana, Aldrin Fadhilan (2022) Klasifikasi Berita Online Tribunnews Menggunakan Metode Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 1061171000088_Undergraduate_Theses.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
1061171000088_Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only until 1 October 2024. Download (1MB) | Request a copy |
Abstract
Era digital saat ini mendorong adanya penyesuain kebiasaan dibidang teknologi yang terus berkembang. Media informasi konvensional koran yang mulai tergantikan dengan portal berita online, salah satunya Tribunnews.com. Portal berita online tersebut tidak menutupi kemungkinan adanya kesalahan informasi yang disampaikan, berupa tidak selarasnya informasi berita yang dituliskan terhadap kategori berita
yang disematkan. Tingkat keselarasan artikel berita terhadap kategori tersebut dapat diartikan tingkat ketepatan klasifikasi kategori berita. Ketepatan klasifikasi berita dapat diolah dengan metode Support Vector Machine (SVM) yang telah banyak penelitian menunjukkan hasil ketepatan terbaik, khususnya terkait dengan data jenis teks atau artikel. Metode SVM memiliki 3 kernel yang umum digunakan yatu Liniear, Polinomial dan Radial Basis Function. Kernel tersebut dapat menghasilkan ketepatan klasifikasi kategori berita yang berbeda-beda. Maka dari itu, tujuan penelitian ini diharapkan dapat mengetahui ketepatan klasifikasi kategori berita Tribunnews.com dan mengetahui metode kernel yang sesuai dan terbaik untuk digunakan pada analisis data
teks tersebut. Hasil yang diperoleh pada penelitian ini antara lain ketepatan klasifikasi kategori terbaik adalah kategori Superskor dan metode yang sesuai digunakan pada ketepatan klasifikasi kategori jenis data teks adalah menggunakan metode SVM kernel Linear. =====================================================================================================
The current digital era encourages the adjustment of habits in the field of technology that continues to develop. Conventional information media are newspapers which are starting to be replaced by online news portals, one of which is Tribunnews.com. The online news portal does not rule out the possibility of misinformation being conveyed, in the form of misalignment of the written news information against the embedded news categories. The level of alignment of news articles to these categories can be interpreted as the level of accuracy of classification of news categories. The accuracy of news classification can be processed using the Support Vector Machine (SVM) method, which has many studies showing the best accuracy results, especially related to text or article type data. The SVM method has 3 commonly used kernels, namely Linear, Polynomial and Radial Basis Function. The kernel can produce the accuracy of classification of different news categories. Therefore, the purpose of this study is to determine the accuracy of the classification of Tribunnews.com news categories and to find out the appropriate and best kernel method to be used in analyzing the text data. The results obtained in this study
include the classification accuracy of the best category is the Superscore category and the appropriate method used for the classification accuracy of text data types is using the SVM kernel Linear method.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Support Vector Machine, Ketepatan Klasifikasi, Kernel. |
| Subjects: | Q Science > Q Science (General) Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA278.55 Cluster analysis Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Vocational > 49501-Business Statistics |
| Depositing User: | Aldrin Fadhilan Tirtana |
| Date Deposited: | 30 May 2022 01:14 |
| Last Modified: | 02 Nov 2022 04:13 |
| URI: | http://repository.its.ac.id/id/eprint/94897 |
Actions (login required)
 |
View Item |