Team Peter Brinkmann at SemEval-2019 Task 4: Detecting Biased News Articles Using Convolutional Neural Networks

Michael Färber, Agon Qurdina, Lule Ahmedi


Abstract
In this paper, we present an approach for classifying news articles as biased (i.e., hyperpartisan) or unbiased, based on a convolutional neural network. We experiment with various embedding methods (pretrained and trained on the training dataset) and variations of the convolutional neural network architecture and compare the results. When evaluating our best performing approach on the actual test data set of the SemEval 2019 Task 4, we obtained relatively low precision and accuracy values, while gaining the highest recall rate among all 42 participating teams.
Anthology ID:
S19-2180
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Editors:
Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1032–1036
Language:
URL:
https://aclanthology.org/S19-2180
DOI:
10.18653/v1/S19-2180
Bibkey:
Cite (ACL):
Michael Färber, Agon Qurdina, and Lule Ahmedi. 2019. Team Peter Brinkmann at SemEval-2019 Task 4: Detecting Biased News Articles Using Convolutional Neural Networks. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1032–1036, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
Team Peter Brinkmann at SemEval-2019 Task 4: Detecting Biased News Articles Using Convolutional Neural Networks (Färber et al., SemEval 2019)
Copy Citation:
PDF:
https://aclanthology.org/S19-2180.pdf
Code
 michaelfaerber/SemEval2019-Task4