Fuzzy multi-task learning for hate speech type identification

Liu, Han ORCID: https://orcid.org/0000-0002-7731-8258, Burnap, Peter ORCID: https://orcid.org/0000-0003-0396-633X, Alorainy, Wafa and Williams, Matthew L. ORCID: https://orcid.org/0000-0003-2566-6063 2019. Fuzzy multi-task learning for hate speech type identification. Presented at: The Web Conference 2019, San Francisco, CA, USA, 13-17 May 2019. WWW '19 The World Wide Web Conference. ACM, pp. 3006-3012. 10.1145/3308558.3313546

Preview

PDF - Accepted Post-Print Version Download (576kB) | Preview

Abstract

In traditional machine learning, classifiers training is typically un-dertaken in the setting of single-task learning, so the trained classi-fier can discriminate between different classes. However, this must be based on the assumption that different classes are mutually exclusive. In real applications, the above assumption does not always hold. For example, the same book may belong to multiple subjects. From this point of view, researchers were motivated to formulate multi-label learning problems. In this context, each instance can be assigned multiple labels but the classifiers training is still typically undertaken in the setting of single-task learning. When probabilistic approaches are adopted for classifiers training, multi-task learning can be enabled through transformation of a multi-labelled data set into several binary data sets. The above data transformation could usually result in the class imbalance issue. Without the above data transformation, multi-labelling of data results in an exponential increase of the number of classes, leading to fewer instances for each class and a higher difficulty for identifying each class. In addition, multi-labelling of data is very time consuming and expensive in some application areas, such as hate speech detection. In this paper, we introduce a novel formulation of the hate speech type identification problem in the setting of multi-task learning through our proposed fuzzy ensemble approach. In this setting, single-labelled data can be used for semi-supervised multi-label learning and two new metrics (detection rate and irrelevance rate) are thus proposed to measure more effectively the performance for this kind of learning tasks. We report an experimental study on identification of four types of hate speech, namely: religion, race, disability and sexual orientation. The experimental results show that our proposed fuzzy ensemble approach outperforms other popular probabilistic approaches, with an overall detection rate of 0.93.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics Social Sciences (Includes Criminology and Education)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher:	ACM
ISBN:	978-1-4503-6674-8
Funders:	Economic and Social Research Council, RAND Corporation
Related URLs:	Organisation
Date of First Compliant Deposit:	5 March 2019
Date of Acceptance:	21 January 2019
Last Modified:	05 Jan 2024 06:17
URI:	https://orca.cardiff.ac.uk/id/eprint/120177

Citation Data

Cited 15 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item