Corpus ID: 236034396

Pseudo-labelling Enhanced Media Bias Detection

@article{Ruan2021PseudolabellingEM,
  title={Pseudo-labelling Enhanced Media Bias Detection},
  author={Qin Ruan and Brian Mac Namee and Ruihai Dong},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.07705}
}
Leveraging unlabelled data through weak or distant supervision is a compelling approach to developing more effective text classification models. This paper proposes a simple but effective data augmentation method, which leverages the idea of pseudolabelling to select samples from noisy distant supervision annotation datasets. The result shows that the proposed method improves the accuracy of biased news detection models. 

Figures and Tables from this paper

References

SHOWING 1-6 OF 6 REFERENCES
A Challenging Dataset for Bias Detection: The Case of the Crisis in the Ukraine
TLDR
A new dataset related to the Ukrainian Crisis of 2014–2015 is presented which can be used by other researchers to train, test, and compare bias detection algorithms, and this dataset can serve as an incisive test of new approaches. Expand
A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media
TLDR
A unified model which can learn from out-of-domain corpora and in-domain unannotated texts and outperform existing methods for NER in Chinese social media is proposed. Expand
Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks
TLDR
This simple and efficient method of semi-supervised learning for deep neural networks is proposed, trained in a supervised fashion with labeled and unlabeled data simultaneously and favors a low-density separation between classes. Expand
SemEval-2019 Task 4: Hyperpartisan News Detection
TLDR
The goal of this SemEval task was to shed light on the state of the art of hyperpartisan news detection, and developed new resources, including a manually labeled dataset with 1,273 articles, and a second dataset with 754,000 articles, labeled via distant supervision. Expand
Team Bertha von Suttner at SemEval-2019 Task 4: Hyperpartisan News Detection using ELMo Sentence Representation Convolutional Network
TLDR
The participation of team “bertha-von-suttner” in the SemEval2019 task 4 Hyperpartisan News Detection task uses sentence representations from averaged word embeddings generated from the pre-trained ELMo model with Convolutional Neural Networks and Batch Normalization for predicting hyperpartisan news. Expand
Political Polarization and the Electoral Effects of Media Bias
Many political commentators diagnose an increasing polarization of the U.S. electorate into two opposing camps. However, in standard spatial voting models, changes in the political preferenceExpand