Applying authorship analysis to extremist-group web forum messages

被引：213

作者：

Abbasi, A ^{[1
]}

Chen, HC ^{[1
]}

机构：

[1] Univ Arizona, Dept Management Informat Syst, Artificial Intelligence Lab, Tucson, AZ 85721 USA

来源：

IEEE INTELLIGENT SYSTEMS | 2005年 / 20卷 / 05期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/MIS.2005.81

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The advantages of applying authorship analysis to extremist-group Web forum messages are discussed. Evaluating the linguistic features of Web messages and comparing them to known writing styles offers the intelligence community a tool for identifying patterns of terrorist communication. Authorship characterization attempts to formulate an author profile by making inferences about gender, education, and cultural backgrounds on the basis of writing style. The research showed significant discrimination power in the application of authorship identification techniques to English and Arabic extremist group forum messages.

引用

页码：67 / 75

页数：9

共 14 条

[1]

Al-Fedaghi S., 1989, P 11 NAT COMP C EXH, P391

[2]

BEESLEY K, 1996, P COLING 96, V1, P89

[3]

Burrows J. F., 1987, Literary & Linguistic Computing, V2, P61, DOI 10.1093/llc/2.2.61

[4]

de Vel O, 2001, SIGMOD REC, V30, P55, DOI 10.1145/604264.604272

[5]

DEROECK AN, 2000, P ASS COMP LING ACL

[6]

Hmeidi I, 1997, J AM SOC INFORM SCI, V48, P867, DOI 10.1002/(SICI)1097-4571(199710)48:10<867::AID-ASI3>3.0.CO

[7]

2-#

[8]

LARKEY LS, 2001, P 10 TEXT RETR C TRE

[9] An emerging model of Web site design for marketing [J].

Palmer, JW ;

Griffith, DA .

COMMUNICATIONS OF THE ACM, 1998, 41 (03) :44-51

[10]

Peng F., 2003, 10 C EUR CHAPT ASS C

← 1 2 →