Abstract

In the era of social media and mobile internet, the design of automatic tools for online detection of hate speech and/or abusive language becomes crucial for society and community empowerment. Nowadays of current technology in this respect is still limited and many service providers are still relying on the manual check. This paper aims to advance in this topic by leveraging novel natural language processing, machine learning, and feature engineering techniques. The proposed approach advocates a classification-like technique that makes use of a special data design procedure. The latter enforces a balanced training scheme by exploring the negativity of the original dataset. This generates new transfer learning paradigms, Two classification schemes using convolution neural network and LSTN architecture that use FastText embeddings as input features are contrasted with baseline models constituted of Logistic regression and Naives’ Bayes classifiers. Wikipedia Comment dataset constituted of Personal Attack, Aggression and Toxicity data are employed to test the validity and usefulness of the proposal.