Hate speech is abusive or stereotyping speech against a group of people, based on characteristics such as race, religion, sexual orientation and gender. Internet and social media have made it possible to spread hatred easily, fast and anonymously. The large scale of data produced through social media platforms requires the development of effective automatic methods to detect such content. Hate speech detection in short text on social media becomes an active research topic in recent years as it differs from traditional information retrieval for documents. My research is to develop a method to effectively detect hate speech based on deep learning techniques. I have proposed a novel feature based on lexicon for short text. Experiments have shown that proposed deep neural network based model improves performance when novel feature combines with CNN and SVM. A comprehensive evaluation with two benchmarking datasets demonstrates the better performance of our model than existing approaches.
Previous Article in event
Next Article in event
Next Article in session
Hate Speech Detection combining CNN and SVM: Performance based upon a novel feature detection
Published:
02 December 2022
by MDPI
in The 3rd International Electronic Conference on Applied Sciences
session Computing and Artificial Intelligence
Abstract:
Keywords: hate speech, CNN, SVM, Feature extraction
![Top](/images/top.png?version=d2a1072bcb778c072486fad356669189)