• Mayur Meghasham Bhavsar
• Salve Sunil
• Hande Shubham
• Gangurde Nandu
• B.A. Abhale

Hate speech on social media platforms has become a major concern in recent years, with many users experiencing online harassment and abuse. In response, automated systems have been developed to detect and flag hate speech, but the effectiveness of these systems is still a subject of debate. In this paper, we present a hate speech detection system for a Twitter-like interface. Our system uses natural language processing techniques to analyze user posts and identify hate speech, and blocks users who repeatedly violate our hate speech policy. We evaluate the performance of our system using a dataset of tweets labelled for hate speech, and compare our results to existing hate speech detection systems. Our findings suggest that our system performs well in identifying hate speech and blocking repeat offenders, but also highlight the challenges of developing fair and unbiased automated systems. We conclude by discussing the implications of our findings for the use of automated hate speech detection on social media platforms, and suggest areas for further research.

Keywords: Deep Learning, Hybrid Word Representation, Hate Speech Detection, Distributed Representation, Symbolic Representation, Neural Network, Linguistic Properties, Part-Of-Speech Tags, Dependency Relationships, Benchmark Dataset, Generalization

"DEEP LEARNING BASED HYBRID WORD REPRESENTATION FOR DETECTION OF HATE SPEECH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.l167-l172, April-2023, Available :http://www.jetir.org/papers/JETIR2304B29.pdf

"DEEP LEARNING BASED HYBRID WORD REPRESENTATION FOR DETECTION OF HATE SPEECH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. ppl167-l172, April-2023, Available at : http://www.jetir.org/papers/JETIR2304B29.pdf