The Detection of Sexual Harassment and Chat Predators Using Artificial Neural Network

• Main Authors: Dhannoon, B.N (Author), Hamzah, N.A (Author)
• Format: Article
• Language: English
• Published: University of Kerbala 2021
• Subjects: Deep learning; Natural Language Processing; Sentiment Analysis; Sexual Predators; Word embedding; XGBoost
• Online Access: View Fulltext in Publisher

 The vast increase in using social media sites like Twitter and Facebook led to frequent sexual-harassment on the Internet, which is considered a major societal problem. This paper aims to detect sexual-harassment and cyber-predators in early phase. We used deeplearning like Bidirectionallylong- short-term memory. Word representations are carefully reviewed in text specific to mapping to real number vectors. The chat sexual predators Detection-approach with the proposed-model. The best results obtained by the performance measured with F0.5-score were the result is-0.927 with proposed-models. The accuracy measured is-97.27% in the proposed-model. The comments sexual-harassment Detection-approach the result is-0.925 F0.5-score, and accuracy measured is-99.12%. © 2021 University of Kerbala.