Open AccessSpam Detection and Hate Speech Identification
Author(s) -
Tanya Sharan,
Aarushi Dhaka,
Divyansh Jain
Publication year - 2022
Publication title -
international journal of advanced research in science, communication and technology
Language(s) - English
Resource type - Journals
ISSN - 2581-9429
DOI - 10.48175/ijarsct-2579
Subject(s) - emoji , computer science , relevance (law) , identification (biology) , identity (music) , sort , flexibility (engineering) , natural language processing , binary classification , speech recognition , computer security , artificial intelligence , internet privacy , social media , world wide web , support vector machine , information retrieval , statistics , botany , physics , mathematics , biology , political science , acoustics , law
The utilization of the term “spam” to explain this sort of invasive blanket-messaging. These are messages sent or comments given to multiple recipients who failed to provoke them. The issues caused by spam are because of the mixture of the unsolicited and bulk aspects; the amount of unwanted messages swamps messaging systems and drowns out the messages that recipients do want. there's no legal definition of hate speech. It can be understood as any quite communication in speech, writing or behavior that attacks or discriminatory language with relevance an individual or a gaggle on the idea of who they're, in other words, supported their religion, ethnicity, nationality, race, color, descent, gender or other identity factor. During this paper, we aim to perform binary classification of spam and hate speech with the assistance of concepts regarding computing, language Processing and Machine Learning. We aim to supply the user with the flexibility to classify the message as fake or real. We have even incorporated the emoji feature further i.e., the user can enter messages with emoji and our model is ready to classify it.