As a signal of more and more distinguished on-line networking, cyberbullying has developed as a big issue harassing kids, adolescents and vernal grown-ups. Machine learning procedures build programmed recognition of harassing messages in web-based social networking doable, and this might build a solid and safe web-based social networking condition. During this important analysis zone, one basic issue is powerful and discriminative numerical portrayal learning of instant messages. During this paper, we tend to propose another portrayal learning strategy to handle this issue. Our technique named Semantic-Enhanced Marginalized Denoising Auto-Encoder (smSDA) is created by means that of linguistics enlargement of the notable profound learning model stacked denoising autoencoder. The linguistics enlargement includes of linguistics dropout commotion and meagerness limitations, wherever the linguistics dropout clamor is planned in sight of area learning and therefore the word inserting system. Our planned strategy will misuse the hid part structure of tormenting knowledge and soak up a full of life and discriminative portrayal of content.

NLP, cyberbullying, Social Network, Mining, collaboration

[1] A. Agarwal, B. Xie, I. Vovsha, O. Rambow and R. Passonneau, "Sentiment Analysis of Twitter Data," In Proceedings of workshop on languages of social media, 2011. pp. 30-38.
[2] A. Agarwal, F. Biadsy, and K. R. Mckeown. "Contextual phrase-level polarity analysis using lexical affect scoring and syntactic n-grams." Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 2009. pp. 24-32.
[3] A. Go, R. Bhayani, L. Huang, “Twitter sentiment classification using distant supervision”, CS224N Project Report, Stanford, 2009. pp. 1-12.
[4] A. Harb, M. Plantié, G. Dray, M. Roche, F. Trousset, and P. Poncelet. "Web Opinion Mining: How to extract opinions from blogs?" In Proceedings of the 5th international conference on Soft computing as transdisciplinary science and technology, ACM, 2008. pp. 211-217.
[5] A. Pak, and P. Paroubek “Twitter as a corpus for sentiment analysis and opinion mining,” Proceedings of the seventh International Conference on Language Resource and Evolution (LREC’10), 2010. pp. 19-21.
[6] B. O`Connor, R. Balasubramanyan, B. R. Routledge, and N. A. Smith. "From tweets to polls: Linking text sentiment to public opinion time series." ICWSM 11, no. 122-129 ,2010. pp. 1-2.
[7] B. Pang, L. Lee, and S. Vaithyanathan. "Thumbs up? : sentiment classification using machine learning techniques."Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10. Association for Computational Linguistics, 2002. pp. 79-86.
[8] C. Whitelaw, N. Garg, and S. Argamon "Using appraisal groups for sentiment analysis," presented at the Proceedings of the 14thACM international conference on Information and knowledge management, Bremen, Germany, 2005.
[9] D. M. Haughton, J. J. Xu, D. J. Yates, X. Yan “Introduction to Data Analytics and Data Mining for Social Media Minitrack”, 49th Hawaii International Conference on System Sciences, 2016.p. 1414.
[10] D. M. Law, J. D. Shapka, and B. F. Olson. "To control or not to control? Parenting behaviours and adolescent online aggression." Computers in Human Behavior 26.6,2010 pp.1651-1656.
[11] D. Quinn, C. Liming, and M. Maurice "Does age make a difference in the behaviour of online social network users?"Internet of Things (iThings/CPSCom).