Implementation of Bad Information Filtering System Based on SVM Algorithm

Xiao-Lan Xie, Zhen Long
2016 International Journal of Security and Its Applications  
This paper puts forward text filtering system based on SVM algorithm regarding to the problem that bad and sensitive information of user tag that may exist in the collaborative geographic information plotting system. Then further improvement has been made towards the TF-IDF for feature extraction and thus achieved the function that automatically blocks the bad and sensitive information marked by users. dimensions. If there are no dimension cuts, then dimension disaster would occur and thus stop
more » ... occur and thus stop words after Chinese word segmentation should be cut such as "的", "了", "我的" and "可以" etc. After traversing directories and files of the data set, text segmentation could be made and finally forms a dictionary model. This design makes the pretreatment after word segmentation process and automatically removes spaces between words and other various characters so as to get rid of the camouflage function of the bad and sensitive information, which can be shown in Figure 1 . Authors Xiao-lan Xie, She got her PhD in Xidian University, Shan Xi, China. She is a Professor in School of information science and engineering, Guilin University of Technology. Areas of research include Cloud computing, Grid computing and Intelligent Decision System. She is a committee member and deputy secretary general of Cloud computing expert committee of China communication society. She is also a member of China computer society CCF and IEEE CS. Zhen Long, He pursues his master degree in Guilin University of Technology. His research interests include embedded system, machine learning, data mining, etc.
doi:10.14257/ijsia.2016.10.9.06 fatcat:r7w4yr6vmrdabmhdbrzz5n6gua