Authorship Identification of Chinese E-Mail Based on Form Features for Computer Forensic

Abstract:

E-mail has become one of the most important applications on the Internet. At the same time, computer crimes involving e-mail increases rapidly. To prevent these phenomena from happening, the authorship identification methods for Chinese e-mail documents were described in this paper, which could provide evidence for the purpose of computer forensic. E-mail form features to classify authorship were extracted. To classify the author of Chinese e-mail, the SVM(support vector machine) algorithm was adopted to learn the authors features. Experiments gained satisfactory results on limited dataset. The accuracy of dataset for four authors was 92.56%. The satisfactory results showed that it was feasible to apply to computer forensic.

• Periodical: Applied Mechanics and Materials (Volumes 536-537)
• Pages: 578-582
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.536-537.578
• Online since: April 2014
• Authors: Shu Hui Chang*, Gui Fa Teng, Jian Bin Ma
• Keywords: Authorship Identification, Chinese E-Mail, Computer Forensic, Form Features, Support Vector Machine (SVM)

References

[1] Information on http: /www. fraud. org.

[2] F. Mosteller, D. L Wallace: Inference and Disputed Authorship, Addison-Wesley Publishing Company, America, (1964).

[3] W. Elliot, R. Valenza: submitted to Journal of Notes and Queries(1991).

[4] I. Krsul: Authorship analysis: Identifying the author of a program. Technical report, Department of Computer Science, Purdue University, (1994).

[5] I. Krsul, E. Spafford: submitted to Journal of Computers and Security(1997).

[6] P. Sallis, S. MacDonell, G. MacLennan, A. Gray, R. . Kilgour, Identified: Software Authorship Analysis with Case-Based Reasoning, in: Proc. Addendum Session Int. Conf. Neural Info. Processing and Intelligent Info. Systems, 1997, pp.53-56.

[7] Yuta Tsuboi: Authorship Identification for Heterogeneous Documents. Nara Institute of Science and Technology, University of Information Science, Japanese, (2002).

[8] D. V. Olivier, A. Anderson, A. Corney, M. Mohay, Mining e - mail content for author identification forensics, in: ACM Conference on Computer Security-workshop on Data Mining for Security Applications, Philadelphia, PA, (2001).

DOI: 10.1145/604264.604272

[9] T. Guifa, L. Maosheng, M. Jianbin, E-mail authorship mining based on SVM for computer forensic, in: IEEE Systems, Man and Cybernetics Technical Committee on Cybernetics, China, 2004, vol. 2, pp.1204-1207.

[10] Vapnik: The Nature of Statistical Learning Theory, Springer-Verlag, New York, (1998).