Journal of Engineering Research and Reports

Social media has shown to be a medium for the exchange of information, conducting commerce, and even for religious and political activity. The same site has been used to disseminate cyberbullying and hate speech. Cyberbullying is an offense when a perpetrator targets a victim with online provocation and resentment, which has negative impacts on the victim's emotions, relationships, and physical health. These spew forth a lot of hate speech directed at those who have different beliefs or hold different opinions. In order to overcome these problems, this research creates a deeper neural network and maximum entropy-based model for the identification of cyberbullying. In comparison to the present systems, Convolution Neural Network is used for the superior results. The dataset gathered includes 24,783 records tweets with the categories "bullying language," "non-bullying language," and "neither" are included. According to geopolitical zones, tweets are categorized in the study. Throughout the experiment, the dataset was trained and evaluated. The model's unigram performed with 96.3 percent accuracy, the bigram model with 93.8 percent accuracy, the trigram with 88.2 percent accuracy, and the n-gram enhanced performance with 94.2 percent. The two baseline classifiers for the tweets dataset were TF-IDF (Term Frequency Inverse Document Frequency) and the characteristics of unigram, bigram, trigram, and n-grams for detection. The outcome of the model during the tweet cyberbullying will increase the memory accuracy of the bullying. The study's findings will reveal creative language and alternative spellings for cyberbullying in tweets.