TOXIC COMMENT CLASSIFICATION ON SOCIAL MEDIA USING NLP

TOXIC COMMENT CLASSIFICATION ON SOCIAL MEDIA USING NLP

1* RAMA DEVI.G ,2*P.VARSHITH, 3* R.LAXMI KAMAL, 4*S.SONIKA, 5*P. SAI SHIVANI

1 Assistant Professor, 2,3,4,5 B.Tech Final Year

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

NALLA MALLA REDDY ENGINEERING COLLEGE

DIVYANAGAR, HYDERABAD, INDIA.

Abstract-As online content keeps to develop, so does the spread of hate speech. It is the state of abusive or threatening speech or writing that expresses prejudice towards a specific group, specifically on basis of race, religion or sexual orientation. That is affecting absolutely everyone and might be tough for them to tolerate anymore. So, we build an software to be able to discover those abusive feedback that's based totally on NLP (Natural Language Processing). NLP allows computer systems to apprehend natural language as people do. Whether the language is spoken or written, natural language processing makes use of synthetic intelligence to take real world input, procedure it, and make experience of it in a way a PC can apprehend. In this assignment we try to acquire comments from various posts on social media and then try to classify the ones comments as toxic or non-toxic using NLP. After classifying we output a listing of profiles which have published toxic remarks on the publish in conjunction with the remark. This listing can similarly be used by another device or software to delete offensive feedback as well as block the customers posting such remarks.

Keywords-Toxic and non Toxic  Comments, NLP (Natural language Processing),