Mobile Forensics for Cyberbullying Detection using Term Frequency - Inverse Document Frequency (TF-IDF)

Abstract

The case of cyberbullying in Indonesia was ranked third in the world in 2015 and as much as 91% was experienced by children [1]. RSA Anti Fraud Command Center (AFCC) report reports that in 2015 45% of transactions were carried out through mobile channels, while 61% of fraud occurred through mobile devices [2]. WhatsApp in July 2019, 1.6 billion users access the WhatsApp messenger on a monthly basis [10]. The data opens a reference for investigators to better anticipate cybercrime actions that can occur in the whatsapp application because more users are using the application. In this study using the TF-IDF method in detecting cyberbullying that occurs in order to be able to add a reference for investigators. The conclusions that have been obtained from the simulation of conversations between four people in a whatsapp group get the results of the cyberbullying rate that the user "a" has a cyberbullying rate of 66.80%, the user "b" has a cyberbullying rate of 50%, the user "c" has a level cyberbullying is 33.19%, user "c" has a cyberbullying rate of 0% from the data proving that the TF-IDF method can help investigators detect someone who will commit cyberbullying actions but in its development a better way is needed when preprocessing so that the abbreviation or changing words can still be detected perfectly.