Identifying Offensive Expressions of Opinion in Context

TL;DR

This paper introduces a new cross-lingual, context-aware offensive lexicon for identifying offensive opinions and hate speech in Portuguese and English, addressing a gap in subjective information extraction.

Contribution

It presents a novel annotated lexicon of offensive expressions, including explicit and implicit forms, with high annotation reliability, for use in sentiment and hate speech detection.

Findings

High inter-annotator agreement in annotation

Lexicon covers explicit and implicit offensive expressions

Available in Portuguese and English

Abstract

Classic information extraction techniques consist in building questions and answers about the facts. Indeed, it is still a challenge to subjective information extraction systems to identify opinions and feelings in context. In sentiment-based NLP tasks, there are few resources to information extraction, above all offensive or hateful opinions in context. To fill this important gap, this short paper provides a new cross-lingual and contextual offensive lexicon, which consists of explicit and implicit offensive and swearing expressions of opinion, which were annotated in two different classes: context dependent and context-independent offensive. In addition, we provide markers to identify hate speech. Annotation approach was evaluated at the expression-level and achieves high human inter-annotator agreement. The provided offensive lexicon is available in Portuguese and English languages.