期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：20
出版社：Journal of Theoretical and Applied
摘要：Currently, social media is used to express the users� opinion, perception and so on. Status created by social media users describes the characteristics of their personality. This research was conducted to find out the traits of social media users on Facebook by mining the users� Facebook posts. The texts were categorized and classified using SVM, Na�ve Bayes and Logistic Regression in order to get the traits of each user. The data for this case study was taken from Indonesian users of Facebook. The result of this mining was compared to the results of the previous research. To handle the problem of imbalanced user data, synthetic minority over-sampling technique (SMOTE) was used. The results of this study indicated that the results generated using the proposed method successfully outperformed the results of the previous research with an average accuracy of 89.08%.
