Ngejane, Hombakazi CEloff, JHPSefara, Tshephisho JMarivate, VN2021-04-102021-04-102021-03Ngejane, H.C., Eloff, J., Sefara, T.J. & Marivate, V. 2021. Digital forensics supported by machine learning for the detection of online sexual predatory chats. <i>Forensic science international: Digital investigation, 36.</i> http://hdl.handle.net/10204/119662666-2817https://doi.org/10.1016/j.fsidi.2021.301109https://www.sciencedirect.com/science/article/pii/S2666281721000032http://hdl.handle.net/10204/11966Chat-logs are informative digital footprints available on Social Media Platforms (SMPs). With the rise of cybercrimes targeting children, chat-logs can be used to discover and flag harmful behaviour for the attention of law enforcement units. This can make an important contribution to the safety of minors on SMPs from being exploited by online predators. The problem is that digital forensic investigation is mostly manual. Thus, a daunting task for forensic investigators because of the sheer volume and variety of data. The solution that is proposed in this paper employs a Digital Forensic Process Model that is supported by Machine Learning (ML) methods to facilitate the automatic discovery of harmful conversations in chat-logs. ML has already been successfully applied in the domain of text analysis for the discovery of online sexual predatory chats. However, there is an absence of approaches that show how ML can contribute to a digital forensic investigation. Thus, the contribution of this paper is to indicate how the tasks in a digital forensic investigation process can be organised so to obtain useable ML results when investigating online predators.AbstractenCyber safetyCybersecurityDigital forensic investigationMachine learningOnline sexual predatory conversationArticleNgejane, H. C., Eloff, J., Sefara, T. J., & Marivate, V. (2021). Digital forensics supported by machine learning for the detection of online sexual predatory chats. <i>Forensic science international: Digital investigation, 36</i>, http://hdl.handle.net/10204/11966Ngejane, Hombakazi C, JHP Eloff, Tshephisho J Sefara, and VN Marivate "Digital forensics supported by machine learning for the detection of online sexual predatory chats." <i>Forensic science international: Digital investigation, 36</i> (2021) http://hdl.handle.net/10204/11966Ngejane HC, Eloff J, Sefara TJ, Marivate V. Digital forensics supported by machine learning for the detection of online sexual predatory chats. Forensic science international: Digital investigation, 36. 2021; http://hdl.handle.net/10204/11966.TY - Article AU - Ngejane, Hombakazi C AU - Eloff, JHP AU - Sefara, Tshephisho J AU - Marivate, VN AB - Chat-logs are informative digital footprints available on Social Media Platforms (SMPs). With the rise of cybercrimes targeting children, chat-logs can be used to discover and flag harmful behaviour for the attention of law enforcement units. This can make an important contribution to the safety of minors on SMPs from being exploited by online predators. The problem is that digital forensic investigation is mostly manual. Thus, a daunting task for forensic investigators because of the sheer volume and variety of data. The solution that is proposed in this paper employs a Digital Forensic Process Model that is supported by Machine Learning (ML) methods to facilitate the automatic discovery of harmful conversations in chat-logs. ML has already been successfully applied in the domain of text analysis for the discovery of online sexual predatory chats. However, there is an absence of approaches that show how ML can contribute to a digital forensic investigation. Thus, the contribution of this paper is to indicate how the tasks in a digital forensic investigation process can be organised so to obtain useable ML results when investigating online predators. DA - 2021-03 DB - ResearchSpace DP - CSIR J1 - Forensic science international: Digital investigation, 36 KW - Cyber safety KW - Cybersecurity KW - Digital forensic investigation KW - Machine learning KW - Online sexual predatory conversation LK - https://researchspace.csir.co.za PY - 2021 SM - 2666-2817 T1 - Digital forensics supported by machine learning for the detection of online sexual predatory chats TI - Digital forensics supported by machine learning for the detection of online sexual predatory chats UR - http://hdl.handle.net/10204/11966 ER -24283