Authorship Authentication Using Short Messages from Social Networking Sites

被引:9
作者
Li, Jenny S. [1 ]
Monaco, John V. [1 ]
Chen, Li-Chiou [1 ]
Tappert, Charles C. [1 ]
机构
[1] Pace Univ, Seidenberg Sch Comp Sci & Informat Syst, White Plains, NY 10606 USA
来源
2014 IEEE 11TH INTERNATIONAL CONFERENCE ON E-BUSINESS ENGINEERING (ICEBE) | 2014年
关键词
Authorship authentication; stylometry; social network; language-based security; intrusion detection;
D O I
10.1109/ICEBE.2014.61
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper presents and discusses several experiments in authorship authentication of short social network postings, an average of 20.6 words, from Facebook. The goal of this research is to determine the degree to which such postings can be authenticated as coming from the purported user and not from an intruder. Various sets of stylometry and ad hoc social networking features were developed to categorize short messages from thirty Facebook authors as authentic or non-authentic using Support Vector Machines. The challenges of applying traditional stylometry on short messages were discussed. The test results showed the impact of sample size, features, and user writing style on the effectiveness of authorship authentication, indicating varying degrees of success compared to previous studies in authorship authentication.
引用
收藏
页码:314 / 319
页数:6
相关论文
共 17 条
[1]   Applying authorship analysis to extremist-group web forum messages [J].
Abbasi, A ;
Chen, HC .
IEEE INTELLIGENT SYSTEMS, 2005, 20 (05) :67-75
[2]  
Allison B., 2008, PROC LREC 08
[3]  
Angela O., 2006, P 2006 40 ANN IEEE I
[4]  
[Anonymous], 6 JADT
[5]  
[Anonymous], 2013, BBC TECHNOLOGY 1113
[6]  
[Anonymous], 2002, Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
[7]  
Corney M, 2002, P 18 ANN COMP SEC AP
[8]   SUPPORT-VECTOR NETWORKS [J].
CORTES, C ;
VAPNIK, V .
MACHINE LEARNING, 1995, 20 (03) :273-297
[9]  
Iqbal F., 2010, P 2010 ACM S APPL CO
[10]  
KEARNS M, 1997, ALGORITHMIC STABILIT