Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Faturrahman Muhammad Suryana
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Klasifikasi Jenis Berita pada Sosial Media Twitter menggunakan Algoritme Support Vector Machine (SVM) Faturrahman Muhammad Suryana; Imam Cholissodin; Edy Santoso
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 6 (2020): Juni 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Twitter is a social media that is still very popular in Indonesia. Not just for communication, Twitter now become one of the fastest way of spreading information. One of information that disseminated by Twitter is news. This thing is proven by the large number of followers in online news media's Twitter account such as @detikcom that has over fifteen million followers on its Twitter account. Nowadays, news tweets on Twitter are not categorized into categories based on the discussion in that news. This research is conducted to classify the categories of the news on Twitter to make user easily find the category of the news that users want to find. One of algorithm that can be applied to do classification is Support Vector Machine (SVM). This research use multi-class SVM algorithm with one against all method with classes as many as 5 type of classes. Before proceeding to SVM algorithm process, preprocessing and term weighting is processed first. Parameter-parameter that are used by this research are ratio of training data and test data 90%:10%, lambda = 0.1, complexity = 0.001, learning rate = 0.0001, and epsilon = 0.0001. The average accuracy value in this research is 0.85.
Co-Authors Edy Santoso Imam Cholissodin