Evaluating Classifiers in Detecting 419 Scams in Bilingual Cybercriminal Communities
This work addresses the problem of detecting cybercrime scams for cybersecurity applications, but it is incremental as it applies existing methods to a new bilingual dataset.
The paper evaluated three machine learning classifiers (Naive Bayes, k-nearest neighbors, and SVM) for detecting 419 scams in a bilingual Nigerian cybercriminal community, finding that SVM significantly outperformed the others at a 95% confidence level.
Incidents of organized cybercrime are rising because of criminals are reaping high financial rewards while incurring low costs to commit crime. As the digital landscape broadens to accommodate more internet-enabled devices and technologies like social media, more cybercriminals who are not native English speakers are invading cyberspace to cash in on quick exploits. In this paper we evaluate the performance of three machine learning classifiers in detecting 419 scams in a bilingual Nigerian cybercriminal community. We use three popular classifiers in text processing namely: Naïve Bayes, k-nearest neighbors (IBK) and Support Vector Machines (SVM). The preliminary results on a real world dataset reveal the SVM significantly outperforms Naïve Bayes and IBK at 95% confidence level.