Challenges in discriminating profanity from hate speech. Issue 2 (4th March 2018)

• Record Type: Journal Article
• Authors: Malmasi, Shervin; Zampieri, Marcos
• Is Part Of: Journal of experimental & theoretical artificial intelligence. Volume 30:Issue 2(2018)
• Page Start: 187
• Page End: 202
• Publication Date: 2018-03-04
• Subjects: Hate speech -- social media -- bullying -- twitter -- text classification -- classifier ensembles; Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/0952813X.2017.1409284
• Languages: English
• ISSNs: 0952-813X

Abstract

ABSTRACT: In this study, we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes -grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalisation, achieving the best result of accuracy for this 3-class classification task. Analysis of the results reveals that discriminating hate speech and profanity is not a simple task, which may require features that capture a deeper understanding of the text not always possible with surface -grams. The variability of gold labels in the annotated data, due to differences in the subjective adjudications of the annotators, is also an issue. Other directions for future work are discussed.