Abstract: Cyber bullying has emerged as a serious problem among the various effects of Social Media. It is afflicting children, adolescents and young adults. Machine learning techniques make automatic detection of bullying messages in social media is possible, and this could help to construct a healthy and safe social media environment. Robust and discriminative numerical representation learning of text messages is the critical issue in the research area. In this paper, we propose a new representation of learning method to tackle this problem. Our method is developed via semantic extension of the popular deep learning model stacked denoising auto encoder which is named as Semantic-Enhanced Marginalized Denoising Auto-Encoder (smSDA). The semantic extension consists of semantic dropout noise and sparsely constraints. Where the semantic dropout noise is designed based on domain knowledge and the word embedding technique. Our proposed method is able to exploit the hidden feature i.e., structure of bullying information and learn a robust and discriminative representation of text.
Keywords: Social Media, Bullying, Machine Learning, Safe Environment.
| DOI: 10.17148/IJARCCE.2022.11108