UMN Knowledge Center

Manchester United Soccer Team News Classification using Support Vector Machine

Putra, Theodore Adi and Tonara, David Boy (2017) Manchester United Soccer Team News Classification using Support Vector Machine. In: Proceedings of 2017 International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS 2017), 08 November 207, Yogyakarta.

Full text not available from this repository.

Abstract

Soccer is a sport that has many fans. One of the soccer team that has many fans is Manchester United. Todays, media online has been developing rapidly and it can spread through the media online vastly. Therefore, categorizing the news is an important matter to help the Manchester United fans gaining news accurately. There are many techniques to classify data, one of them is Support Vector Machine (SVM). SVM is a technique that mostly used to classifying news content. SVM has an advantage that can identify separated hyperplane and maximized margin between two or more different class. This research is using Python programming language to perform news crawler that came from detik.com and kompas.com, pinpointing words using TF-IDF algorithm and classifying news with SVM binary and multiclass so it can produce classified news about Manchester United soccer team. Furthermore, the result of classification is used to make portal news about soccer team Manchester United.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Support Vector Machine, News Classification, Text Mining, Python, Manchester United, Soccer News
Subjects: T Technology > T Technology (General)
T Technology > T Technology (General) > T55 Industrial engineering. Management engineering > T58.5-58.64 Information technology
T Technology > T Technology (General) > T55 Industrial engineering. Management engineering > T59.5 Automation
Divisions: Universitas Multimedia Nusantara
Depositing User: mr admin umn
Date Deposited: 01 Mar 2018 04:07
Last Modified: 25 Apr 2018 06:26
URI: http://kc.umn.ac.id/id/eprint/2780

Actions (login required)

View Item View Item