Stage-oe-small.jpg

Inproceedings3769

Aus Aifbportal
Wechseln zu:Navigation, Suche


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


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



Published: 2019

Buchtitel: Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval∂NAACL-HLT’19)
Verlag: Association for Computational Linguistics

Referierte Veröffentlichung

BibTeX

Kurzfassung
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 dataset 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.

Download: Media:SemEval_2019_Task_4.pdf
Weitere Informationen unter: Link



Forschungsgruppe

Web Science


Forschungsgebiet