期刊名称：TELKOMNIKA (Telecommunication Computing Electronics and Control)
印刷版ISSN：2302-9293
出版年度：2017
卷号：15
期号：1
页码：357-364
DOI：10.12928/telkomnika.v15i1.4557
语种：English
出版社：Universitas Ahmad Dahlan
摘要：News curators in twitter are a user, which is interested in following, spreading, giving feedback of recent popular articles. There are two kinds of this user, news curator as human user and news aggregator as bot user. In prior works about news curator, the classification system built using followers, URL, mention and retweet feature. However, there are limited prior works for classifiying Indonesian News Curator in twitter and still hard for labelling data involve just two features: followers and URL. In this paper, we proposed a framework for classifying Indonesian news curator in twitter using Naïve Bayes Classifier (NBC) and added features such as location, bio profile, and common tweet. Another purpose for analysing the influential features of certain class, so its make easier for labelling data of this role in the future. Examination result using percentage split as evaluating system produced 87% accuracy. The most influential features for news curator are followers, bio profile, mention and retweet. For news aggregator class are followers, location, and URL. The rest just common tweet feature for not both class. We implemented Feature Subset Selection (FSS) for increasing system performance and avoiding the over fitting data, it has produced 92.90% accuracy.
其他摘要：News curators in twitter are a user, which is interested in following, spreading, giving feedback of recent popular articles. There are two kinds of this user, news curator as human user and news aggregator as bot user. In prior works about news curator, the classification system built using followers, URL, mention and retweet feature. However, there are limited prior works for classifiying Indonesian News Curator in twitter and still hard for labelling data involve just two features: followers and URL. In this paper, we proposed a framework for classifying Indonesian news curator in twitter using Naïve Bayes Classifier (NBC) and added features such as location, bio profile, and common tweet. Another purpose for analysing the influential features of certain class, so its make easier for labelling data of this role in the future. Examination result using percentage split as evaluating system produced 87% accuracy. The most influential features for news curator are followers, bio profile, mention and retweet. For news aggregator class are followers, location, and URL. The rest just common tweet feature for not both class. We implemented Feature Subset Selection (FSS) for increasing system performance and avoiding the over fitting data, it has produced 92.90% accuracy.
