Content area
Full text
Abstract
The massive proliferation of social media has opened possibilities for the perpetrator conducting the crime of online child grooming. Because the pervasiveness ofthe problem scale, it may only be tamed effectively and efficiently by using an automatic grooming conversation detection system. The current study intends to address the issue by using Support Vector Machine and k-nearest neighbors' classifiers. Besides, the study also proposes a low-computational cost classification method, which classifies a conversation using the number of the existing grooming conversation characteristics. All proposed methods are evaluated using 150 textual conversations of which 105 are grooming, and 45 are nongrooming. We identify that grooming conversations possess 17 features of grooming characteristics. The results suggest that the SVM and k-NN can identify grooming conversations at 98.6% and 97.8% of the level of accuracy. Meanwhile, the proposed simple method has 96.8% accuracy. The empirical study also suggests that two among the seventeen characteristics are insignificant for the classification.
Keywords: online child grooming; support vector machine; k-nearest neighbors; grooming classifier
Copyright © 2018 Universitas Ahmad Dahlan. All rights reserved.
1.Introduction
Online child grooming is defined as a process to approach, persuade, and engage a child, the vctim, in sexual activity by using the Internet as a medium. Perpetrators approach the vctim to build not only sexual but also emotional relationship [1]. The massive proliferation of social media has opened possibilities for the perpetrators to conduct the crime of online child grooming in a larger sale [2]. According to the Child Exploitation and Online Protection Agency, online child grooming is the most reported crime in the UK in 2009-2010 [2]. It affects the victim life psychologically, physically, emotionally, behaviorally, and psycho-socially [3].
For revealing this type of crimes, investigator usually relies on the conversation texts where the grooming patterns are carefully analyzed [4]. With the vast amount of textual conversation data, the process becomes severe and requires a significant amount of time. The manual approach of investigating grooming pattern is also error Rome [4]; besides, the grooming process may take minutes, hours, days, or months [5-7].
For the reason described above, it is important to develop an automatic system to analyze a conversation text and to detect the possibility of the online child grooming conversation. During the last...