Alert System for Controlling Cyberbullying Words Using Fuzzy Logic and Fuzzy Inference Engine

Abstract

Cyberbullying is a socially aggressive and has powerful negative effects for individuals, specifically adolescents and youngsters. Cyberbullying allows the offender to mask his or her identity behind a computer. This anonymity makes it easier for the offender to strike blows against a victim without having to see the victim’s physical response. The distancing effect that technological devices have on today’s youth often leads them to say and do crueler things compared to what is typical in a traditional face-to-face bullying situation. In the recent times many methods for automatic thoughts of mining in the online data are becoming increasingly important, to increase the safety parameter of the people. This framework is proposed to extract Cyberbully polarity from the Forum using Fuzzy logic technique. At first, the given input is pre-processed and the useful content is gathered. Subsequently, the pre -processed data will be sent to the features extraction method. Probabilities of the words are calculated by using Fuzzy Decision Tree Method. Fuzzy rules can be applied in all these features to extract the certain set of cyberbully words like bad words, insulting words,threatening words and terrorism words from the given input, hence we use text mining here. Finally this method will return the reduced and accurate cyberbully words. This method is performed by human annotation using the existing methods like Mamdani Fuzzy System and Naive Bayes classifier. Extensive experiments are performed by using fuzzy logic on crime debate forum and the results show that this proposed approach is better than the traditional one. Aggressive text detection in social networks allows identifying offenses and misbehavior, and leverages tasks such as cyberbullying detection. Social media became a very useful platform to express ourselves. The expressions have adverse reactions as well. We intend to take data from these platforms and make use of it to improve on the safety parameter. For the development of the system we take the data available on Twitter and filter all the useful contents.