Uma Abordagem para Identificar e Monitorar Haters em Redes Sociais Online

• Thais G. Almeida UFAM
• Fabíola G. Nakamura UFAM
• Eduardo F. Nakamura UFAM

Resumo

Hate speeches published and difused via online environments have the potential to cause harm and suffering to individuals, and lead to social disorder beyond cyber space. In this context, we propose a novel approach to identify and monitor groups of users which propagate such contents. As preliminary results, we detail a methodology for hate speech identification based on Information Theory quantifiers (entropy and divergence) to represent documents. The results show that our methodology overperforms techniques that use data representation, such as TF-IDF and unigrams combined to text classifiers, achieving an F1-score of 86%, 84% e 96% for classifying hate, offensive, and regular speech classes, respectively. Compared to the baselines, our proposal is a win-win solution that improves efficacy (F1-score) and efficiency (by reducing the dimension of the feature vector). The proposed solution is up to 2.27 times faster than the baseline.