Abstract

The vast increase in using social media sites like Twitter and Facebook led to frequentsexual_harassment on the Internet, which is considered a major societal problem. This paper aims todetect sexual_harassment and cyber_predators in early phase. We used deeplearning like Bidirectionallylong-short-term memory. Word representations are carefully reviewed in text specifc to mapping to realnumber vectors. The chat sexual predators Detection_approach with the proposed_model. The bestresults obtained by the performance measured with F0.5-score were the result is_0.927 withproposed_models. The accuracy measured is_97.27% in the proposed_model. The commentssexual_harassment Detection_approach the result is_0.925 F0.5-score, and accuracy measuredis_99.12%.

Keywords

The article was added to IASJ on 2021-12-25

68 Total full text downloads since the date of addition