Cyberbullying

Social media allows people interact to express their thoughts or feelings about different subjects. However, some of users may write offensive twits to other via social media which known as cyber bullying. Successful prevention depends on automatically detecting malicious messages. Automatic detection of bullying in the text of social media by analyzing the text "twits" via one of the machine learning algorithms. In this paper, we have reviewed algorithms for automatic cyberbullying detection in Arabic of machine learning, and after comparing the highest accuracy of these classifications we will propose the techniques Ridge Regression (RR) and Logistic Regression (LR), which achieved the highest accuracy between the various techniques applied in the automatic cyberbullying detection in English and between the techniques that was used in the sentiment analysis in Arabic text, The purpose of this work is applying these techniques for detecting cyberbullying in Arabic.

Among the common crimes and deviations in virtual social networks, the crime of verbal abuse (insult) against women is the most prevalent and common. Some characteristics of social networks, such as the remoteness of communication, being virtual and intangible, the possibility of anonymity, are effective in explaining the high number of these crimes. These features give criminals the opportunity to excuse their actions with ease and lessen the twinge in their conscience. However, the main source of women's victimization should be found in the human interactions of cyber space and not its structure. Criminals sometimes justify their behavior by denying responsibility or denying injury and sometimes with the thought that the victim deserves the crime. This article tries to reveal the cause and manner of verbal abuse against women in Telegram social network. For this purpose, the analysis has been built upon the methods of a criminological theory known as the theory of "neutralization techniques". The data was collected through observation and indirect interview and the method used to analyze this data is descriptive-analytical. The findings of this research indicate that in the case of the slightest unusual behavior of a female user, she faces more and more severe reactions than in the same case for a man. Regarding their abusive behavior, they consider the virtual and intangible nature of the injuries or the guilt of the victim to be enough to neutralize their conscience.