Unit:
Department of Informatics and TelecommunicationsΠληροφορική
Author:
SPITHAS EVANGELOS
Supervisors info:
Σταματόπουλος Παναγιώτης, Επίκουρος Καθηγητής, Τμήμα Πληροφορικής και Τηλεπικοινωνιών, Εθνικό Καποδιστριακό Πανεπιστήμιο Αθηνών
Original Title:
Hate Speech Detection Using Neural Networks
Translated title:
Hate Speech Detection Using Neural Networks
Summary:
Hate Speech consists the use of abusive or stereotyping speech against a person or a
group of people, based on their race, religion, sexual orientation and gender. In modern
days the Internet and social media made the spread of hatred a lot more easy and fast
than the past, as well as gave people the ability to do so anonymously. The purpose of
this Thesis is to create a model that can detect such content in social media with the use
of Machine Learning.
Firstly, we will define the problem of hate speech detection and discuss about existing
research in this field. Then, we will expand on the necessary theoretical background
information regarding Machine Learning, focusing particularly on the neural networks that will later be used. Following that, we will implement and train our own model built with LSTM neural networks. Finally, we will present and discuss the results of our model.
Main subject category:
Technology - Computer science
Keywords:
Hate Speech, Classification, Natural Language Processing, Neural Networks, Recurrent Neural Networks
