作者: Jianbin Ma , Guifa Teng , Yuxin Zhang , Yueli Li , Ying Li
DOI: 10.1007/978-3-642-01393-5_3
关键词:
摘要: With the increasing popularization of Internet, Internet services used as illegal purposes have become a serious problem. How to prevent these phenomena from happening has major concern for society. In this paper, cybercrime forensic method Chinese web information authorship analysis was described. Various writing-style features including linguistic and structural were extracted. To classify author one document, SVM(support vector machine) algorithm adopted learn author's features. Experiments on blog, BBS e-mail dataset gained satisfactory results. The accuracy blog seven authors 89.49%. results showed that it feasible put application.