Abstract
Analyzing authorship of online texts is an important analysis task in security-related areas such as cybercrime investigation and counter-terrorism, and in any field of endeavor in which authorship may be uncertain or obfuscated. This paper presents an automated approach for authorship analysis using machine learning methods, a robust stylometric feature set, and a series of visualizations designed to facilitate analysis at the feature, author, and message levels. A testbed consisting of 506,554 forum messages, in English and Arabic, from 14,901 authors was first constructed. A prototype portal system was then developed to support feasibility analysis of the approach. A preliminary evaluation to assess the efficacy of the text visualizations was conducted. The evaluation showed that task performance with the visualization functions was more accurate and more efficient than task performance without the visualizations.
Original language | English (US) |
---|---|
Title of host publication | IEEE ISI 2013 - 2013 IEEE International Conference on Intelligence and Security Informatics: Big Data, Emergent Threats, and Decision-Making in Security Informatics |
Pages | 16-20 |
Number of pages | 5 |
DOIs | |
State | Published - 2013 |
Event | 11th IEEE International Conference on Intelligence and Security Informatics, IEEE ISI 2013 - Seattle, WA, United States Duration: Jun 4 2013 → Jun 7 2013 |
Other
Other | 11th IEEE International Conference on Intelligence and Security Informatics, IEEE ISI 2013 |
---|---|
Country | United States |
City | Seattle, WA |
Period | 6/4/13 → 6/7/13 |
Fingerprint
Keywords
- authorship analysis
- online forum
- terrorism
- text visualization
ASJC Scopus subject areas
- Artificial Intelligence
- Information Systems
Cite this
Evaluating text visualization : An experiment in authorship analysis. / Benjamin, Victor; Chung, Wingyan; Abbasi, Ahmed; Chuang, Joshua; Larson, Catherine A.; Chen, Hsinchun.
IEEE ISI 2013 - 2013 IEEE International Conference on Intelligence and Security Informatics: Big Data, Emergent Threats, and Decision-Making in Security Informatics. 2013. p. 16-20 6578778.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Evaluating text visualization
T2 - An experiment in authorship analysis
AU - Benjamin, Victor
AU - Chung, Wingyan
AU - Abbasi, Ahmed
AU - Chuang, Joshua
AU - Larson, Catherine A.
AU - Chen, Hsinchun
PY - 2013
Y1 - 2013
N2 - Analyzing authorship of online texts is an important analysis task in security-related areas such as cybercrime investigation and counter-terrorism, and in any field of endeavor in which authorship may be uncertain or obfuscated. This paper presents an automated approach for authorship analysis using machine learning methods, a robust stylometric feature set, and a series of visualizations designed to facilitate analysis at the feature, author, and message levels. A testbed consisting of 506,554 forum messages, in English and Arabic, from 14,901 authors was first constructed. A prototype portal system was then developed to support feasibility analysis of the approach. A preliminary evaluation to assess the efficacy of the text visualizations was conducted. The evaluation showed that task performance with the visualization functions was more accurate and more efficient than task performance without the visualizations.
AB - Analyzing authorship of online texts is an important analysis task in security-related areas such as cybercrime investigation and counter-terrorism, and in any field of endeavor in which authorship may be uncertain or obfuscated. This paper presents an automated approach for authorship analysis using machine learning methods, a robust stylometric feature set, and a series of visualizations designed to facilitate analysis at the feature, author, and message levels. A testbed consisting of 506,554 forum messages, in English and Arabic, from 14,901 authors was first constructed. A prototype portal system was then developed to support feasibility analysis of the approach. A preliminary evaluation to assess the efficacy of the text visualizations was conducted. The evaluation showed that task performance with the visualization functions was more accurate and more efficient than task performance without the visualizations.
KW - authorship analysis
KW - online forum
KW - terrorism
KW - text visualization
UR - http://www.scopus.com/inward/record.url?scp=84883320316&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84883320316&partnerID=8YFLogxK
U2 - 10.1109/ISI.2013.6578778
DO - 10.1109/ISI.2013.6578778
M3 - Conference contribution
AN - SCOPUS:84883320316
SN - 9781467362115
SP - 16
EP - 20
BT - IEEE ISI 2013 - 2013 IEEE International Conference on Intelligence and Security Informatics: Big Data, Emergent Threats, and Decision-Making in Security Informatics
ER -