Image of KLASIFIKASI JUDUL BERITA BAHASA INDONESIA MENGGUNAKAN METODE SELEKSI FITUR CHI-SQUARE DAN ALGORITMA SUPPORT VECTOR MACHINE (SVM).

Skripsi

KLASIFIKASI JUDUL BERITA BAHASA INDONESIA MENGGUNAKAN METODE SELEKSI FITUR CHI-SQUARE DAN ALGORITMA SUPPORT VECTOR MACHINE (SVM).

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

News is an important source of information in society, and classification of news headlines is a challenge for organizing this information. This research aims to develop software that is able to classify Indonesian news headlines into 3 categories using the Support Vector Machine method with Chi-Square Feature Selection. The SVM method is known as an effective classification algorithm, while chi-square feature selection is used to select important words. in news headlines that differentiate between categories. These selected words are then represented using TF-IDF weighting and used as features to train the SVM model. The data used is a collection of Indonesian language news titles in the categories EDU, FINANCE, SPORT. The research stages include text pre-processing, feature extraction, TFIDF weighting, SVM model training, and classification performance evaluation. The results of classification research using the value C=10 show that by applying a combination of chi-square feature selection with the SVM algorithm, the level of classification accuracy of Indonesian news titles decreases by around 3% compared to without feature selection. This research shows that chi-square feature selection with a linear kernel combined with the SVM algorithm is less effective for classification results. Keywords: Support Vector Machine, Chi-Square, classification accuracy, News Title

Availability
Inventory Code Barcode Call Number Location Status
2407002833T144210T1442102024Central Library (REFERENCES)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1442102024
Publisher
Indralaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xiii, xv hlm.; ilus.; tab.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
518.107
Content Type
Text
Media Type
unmediated
Carrier Type
unspecified
Edition
-
Subject(s)
Support Vector Machine
Prodi Teknik Informatika
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment