A Supervised Multi-class Multi-label Word Embeddings Approach for Toxic Comment Classification

Salvatore Carta, Andrea Corriga, Riccardo Mulas, Diego Recupero, Roberto Saia


Nowadays, communications made by using the modern Internet-based opportunities have revolutionized the way people exchange information, allowing real-time discussions among a huge number of users. However, the advantages offered by such powerful instruments of communication are sometimes jeopardized by the dangers related to personal attacks that lead many people to leave a discussion that they were participating. Such a problem is related to the so-called toxic comments, i.e., personal attacks, verbal bullying and, more generally, an aggressive way in which many people participate in a discussion, which brings some participants to abandon it. By exploiting the Apache Spark big data framework and several word embeddings, this paper presents an approach able to operate a multi-class multi-label classification of a discussion within a range of six classes of toxicity. We evaluate such an approach by classifying a dataset of comments taken from the Wikipedia’s talk page, according to a Kaggle challenge. The experimental results prove that, through the adoption of different sets of word embeddings, our supervised approach outperforms the state-of-the-art that operate by exploiting the canonical bag-of-word model. In addition, the adoption of a word embeddings defined in a similar scenario (i.e., discussions related to e-learning videos), proves that it is possible to improve the performance with respect to solutions employing state-of-the-art word embeddings.


Paper Citation