Cardiff University at SemEval-2019 Task 4: Linguistic features for hyperpartisan news detection

Perez Almendros, Carla ORCID: https://orcid.org/0000-0001-9360-4011, Espinosa-Anke, Luis ORCID: https://orcid.org/0000-0001-6830-9176 and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2019. Cardiff University at SemEval-2019 Task 4: Linguistic features for hyperpartisan news detection. Presented at: SemEval-2019: International Workshop on Semantic Evaluation, Minneapolis, Minnesota, USA, 6-7 June 2019. Association for Computational Linguistics, pp. 929-933. 10.18653/v1/S19-2158

Preview

PDF - Accepted Post-Print Version Download (103kB) | Preview

Abstract

This paper summarizes our contribution to the Hyperpartisan News Detection task in SemEval 2019. We experiment with two different approaches: 1) an SVM classifier based on word vector averages and hand-crafted linguistic features, and 2) a BiLSTM-based neural text classifier trained on a filtered training set. Surprisingly, despite their different nature, both approaches achieve an accuracy of 0.74. The main focus of this paper is to further analyze the remarkable fact that a simple feature-based approach can perform on par with modern neural classifiers. We also highlight the effectiveness of our filtering strategy for training the neural network on a large but noisy training set.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	Association for Computational Linguistics
ISBN:	9781950737062
Related URLs:	Organisation
Date of First Compliant Deposit:	15 May 2019
Last Modified:	27 Feb 2025 14:53
URI:	https://orca.cardiff.ac.uk/id/eprint/122142

Actions (repository staff only)

Edit Item