Email communications analysis: how to use computational intelligence methods and tools?

Negnevitsky, Michael; Lim, Mark J.; Hartnett, JS; Reznik, Leon

doi:10.1109/cihsps.2005.1500603

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To summarize, the best feature extraction technique to represent an email into the VSM is either n-gram or BoW; the best feature representation technique is BR, followed by TF; and the best feature selection method is IG. N-Gram Term Frequency Information Gain [30] NA NA NA [31] NA NA NA [32] N-Gram Binary Representation Information Gain [33] Bag of Words Binary Representation NA [35] Bag of Words Binary Representation Chi-Square [10] Bag of Words Binary Representation Chi-Square, Information Gain [36] Bag of Words Binary Representation NA [34] N-Gram Binary Representation NA [11] N-Gram TFiDF Information Gain [37] N-Gram Term Frequency NA [38] Bag of Words Binary Representation Information Gain [39] Bag of Words Binary Representation Information Gain [40] Bag of Words TFiDF NA [41] N-Gram Term Frequency NA [42] N-Gram Term Frequency NA [43] Bag of Words Term Frequency NA [44] NA NA NA [45] N-Gram Term Frequency NA [47] Bag of Words TF NA [46] N-Gram Binary Representation Information Gain and Gain Ratio [48] N-Gram Binary Representation NA [49] Bag of Words Binary Representation Information Gain and Gain Ratio [50] N-Gram Term Frequency, TFiDF Information Gain and Gain Ratio [51] NA NA NA [53] N-Gram Term Frequency Information Gain and Gain Ratio [52] Bag of Words TFiDF NA [54] Bag of Words TFiDF Chi-Square and Information Gain…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Suspicious Terrorist Emails Using Text Classification: A Review

Mujtaba

Shuib

Raj

et al. 2018

MJCS

View full text Add to dashboard Cite

This paper provides a comprehensive review and analysis of the detection of suspicious terrorist electronic mails (emails) using various phases and methods of text classification. We explored, analyzed, and compared different datasets, features, feature extraction techniques, feature representation techniques, feature selection schemes, text classification techniques, and performance measurement metrics used in the detection of suspicious terrorist e-mails. 30 articles were retrieved from 6 well-known academic databases after rigorous selection. From the study, we found that researchers often generate their own e-mails dataset since there is no public dataset is available in the research area of detecting suspicious terrorist e-mails. In most of the studies, researchers used content and context-based features to detect terrorist e-mails. Our findings also show that the most commonly used feature extraction techniques are the bag of words and n-gram, the most typically applied feature representation schemes are binary representation and term frequency, the most usually adopted feature selection method is information gain,, the most common and most accurate text classification algorithms are naïve bayes, decision trees, and support vector machines, and the widely employed performance measurement metrics are accuracy, precision, and recall. Open research challenges and research issues that involve significant research efforts are also summarized in this review for future researchers in the area of suspicious terrorist e-mail detection using text classification techniques where the critical analysis presented in this paper also provides valuable insights to guide these researchers. Finally, the indicated issues and challenges presented in this paper can be used as future research directions in this area.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Abbasi et al [29] used SVM and DT to detect extremist group messages where SVM obtained 97% accuracy, while DT obtained 90% accuracy. Negnevitsky et al [31] used ANN and fuzzy logic, and they achieved 87% accuracy. Rajaram et al [10] used DT classifier to detect suspicious terrorist e-mails and obtained 95% accuracy.…”

Section: Discussionmentioning

confidence: 99%

Detection of Suspicious Terrorist Emails Using Text Classification: A Review

Mujtaba

Shuib

Raj

et al. 2018

MJCS

View full text Add to dashboard Cite

show abstract

“…Behavior models of individual mobile device users and groups of users can be constructed using statistical or social network analysis techniques [11]. The behavior models are used to establish the normal or expected behavior of mobile users.…”

Section: Sms Message Patternsmentioning

confidence: 99%

Detecting Mobile Spam Botnets Using Artificial immune Systems

Vural¹,

Venter²

2011

Advances in Digital Forensics VII

View full text Add to dashboard Cite

Malicious software infects large numbers of computers around the world. Once compromised, the computers become part of a botnet and take part in many forms of criminal activity, including the sending of unsolicited commercial email or spam. As mobile devices become tightly integrated with the Internet, associated threats such as botnets have begun to migrate onto the devices. This paper describes a technique based on artificial immune systems to detect botnet spamming programs on Android phones. Experimental results demonstrate that the botnet detection technique accurately identifies spam. The implementation of this technique could reduce the attractiveness of mobile phones as a platform for spammers.

show abstract

Using Network Forensics and Artificial Intelligence Techniques to Detect Bot-nets on an Organizational Network

Vural

Venter

2010

2010 Seventh International Conference on Information Technology: New Generations

View full text Add to dashboard Cite

Email communications analysis: how to use computational intelligence methods and tools?

Cited by 3 publications

References 26 publications

Detection of Suspicious Terrorist Emails Using Text Classification: A Review

Detection of Suspicious Terrorist Emails Using Text Classification: A Review

Detecting Mobile Spam Botnets Using Artificial immune Systems

Using Network Forensics and Artificial Intelligence Techniques to Detect Bot-nets on an Organizational Network

Contact Info

Product

Resources

About