• Vaishnavi K R
• Pavitra Bai C
• Suchithra G S
• Priyanka R
• Prashanth H S

: As a symptom of progressively prominent online networking , cyberbullying has risen as a difficult issue tormenting kids, teenagers and youthful grown-ups. Machine learning strategies make programmed discovery of harassing messages in web based life and this could develop a sound and safe online life condition. In this significant research zone, one basic issue is powerful and discriminative portrayal learning technique to handle this issue. Our strategy named semantic enhanced marginalized Denoising Auto-encoder (smSDA) is developed via semantic extension of popular deep learning model stacked Denoising Auto-encoder (SDA). Our proposed technique can exploit the component structure of tormenting data and become familiar with robust and discriminative portrayal of content.

Cyberbullying Detection, Stacked Denoising Auto-encoder, Text Mining, Word Embedding.

"CYBERBULLYING DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.466-469, May-2019, Available :http://www.jetir.org/papers/JETIR1905D68.pdf

"CYBERBULLYING DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp466-469, May-2019, Available at : http://www.jetir.org/papers/JETIR1905D68.pdf