Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{145935,
        author = {MUMMADI VENKATESH and M.KUSUMA},
        title = {Cyber-bullying Detection based on Semantic-Enhanced Marginalized Denoising Auto-Encoder},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {4},
        number = {11},
        pages = {732-741},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=145935},
        abstract = {As a aspect impact of more and more popular social media, cyber-bullying has emerged as a heavy downside afflicting kids, adolescents and young adults. Machine learning techniques build automatic detection of bullying messages in social media potential, and this might facilitate to construct a healthy and safe social media surroundings. during this meaningful  analysis space, one essential issue is powerful and discriminative numerical illustration learning of text messages. during this paper, we tend to propose a brand new illustration learning technique to tackle this downside. Our technique named Semantic-Enhanced Marginalized Denoising Auto-Encoder (smSDA) is developed via semantic extension of the popular deep learning model stacked denoising automobile encoder. The semantic extension consists of semantic dropout noise and scantiness,constraints, wherever the semantic dropout noise is designed supported domain data and therefore the word embedding technique. Our planned technique is in a position to use the hidden feature structure of bullying data and learn a strong and discriminative illustration of text.},
        keywords = {Cyberbullying Detection, Text Mining,Representation Learning, Stacked Denoising Autoencoders, Word Embedding},
        month = {},
        }