Year: 2018
Type: conference-paper
Abstract: The current work has proposed to study and to implement a convolutional neural network (CNN) allied to pre-trained (Wang2Vec and GloVe) and trainable word embeddings for hate speech detection in Portuguese. For sake of comparison, the implementation used different gradient descent optimizer functions (RMSprop, Adagrad, Adadelta and Adam), aiming to contrast the performance at each function. For such task, it were used three datasets of comments in Portuguese, annotated as offensive or not offensive. We have concluded that using this proposed approach the results were superior to those from the baseline, achieving higher F-score and accuracy measures.
Authors: Samuel C. Silva, Adriane B. S. Serapião
Institution: Universidade Estadual Paulista (Unesp)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4392009790