Towards Cyberbullying Detection: Building, Benchmarking and Longitudinal Analysis of Aggressiveness and Conflicts/Attacks Datasets from Twitter

• Published in: IEEE transactions on affective computing pp. 1 - 15
• Main Authors: Ferreira, Paula, Pereira, Nadia, Rosa, Hugo, Oliveira, Sofia, Coheur, Luisa, Francisco, Sofia, Souza, Sidclay, Ribeiro, Ricardo, Carvalho, Joao P., Paulino, Paula, Trancoso, Isabel, Veiga-Simao, Ana Margarida
• Format: Journal Article
• Language: English
• Published: IEEE 2024
• Subjects: Affective computing; Aggression; Biological system modeling; Blogs; Context modeling; Cyberbullying; Data mining; Dataset; Employment; Hate speech; Natural language processing; Offense; Social networks; Toxicology

Offense and hate speech are a source of online conflicts which have become common in social media and, as such, their study is a growing topic of research in machine learning and natural language processing. This article presents two Portuguese language offense-related datasets that deepen the study...