Media Bias in German News Articles : A Combined Approach

Cite This

Files in this item

Checksum: MD5:0314d04fc3a39061a0bad29659f42a5d

SPINDE, Timo, Felix HAMBORG, Bela GIPP, 2021. Media Bias in German News Articles : A Combined Approach. ECML PKDD 2020 Workshops. Ghent, Belgium, Sep 14, 2020 - Sep 18, 2020. In: KOPRINSKA, Irena, ed., Michael KAMP, ed., Annalisa APPICE, ed. and others. ECML PKDD 2020 Workshops : Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases, Proceedings. Cham:Springer International Publishing, pp. 581-590. ISSN 1865-0929. eISSN 1865-0937. ISBN 978-3-030-65964-6. Available under: doi: 10.1007/978-3-030-65965-3_41

@inproceedings{Spinde2021-02-02Media-55901, title={Media Bias in German News Articles : A Combined Approach}, year={2021}, doi={10.1007/978-3-030-65965-3_41}, number={1323}, isbn={978-3-030-65964-6}, issn={1865-0929}, address={Cham}, publisher={Springer International Publishing}, series={Communications in Computer and Information Science}, booktitle={ECML PKDD 2020 Workshops : Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases, Proceedings}, pages={581--590}, editor={Koprinska, Irena and Kamp, Michael and Appice, Annalisa}, author={Spinde, Timo and Hamborg, Felix and Gipp, Bela} }

2021-02-02 Attribution 4.0 International Spinde, Timo Gipp, Bela 2021-12-15T14:23:04Z Gipp, Bela Hamborg, Felix 2021-12-15T14:23:04Z Spinde, Timo Media Bias in German News Articles : A Combined Approach Hamborg, Felix eng Slanted news coverage, also called media bias, can heavily influence how news consumers interpret and react to the news. Models to identify and describe biases have been proposed across various scientific fields, focusing mostly on English media. In this paper, we propose a method for analyzing media bias in German media. We test different natural language processing techniques and combinations thereof. Specifically, we combine an IDF-based component, a specially created bias lexicon, and a linguistic lexicon. We also flexibly extend our lexica by the usage of word embeddings. We evaluate the system and methods in a survey (N = 46), comparing the bias words our system detected to human annotations. So far, the best component combination results in an F<sub>1</sub> score of 0.31 of words that were identified as biased by our system and our study participants. The low performance shows that the analysis of media bias is still a difficult task, but using fewer resources, we achieved the same performance on the same task than recent research on English. We summarize the next steps in improving the resources and the overall results.

Downloads since Dec 15, 2021 (Information about access statistics)

Spinde_2-x72iwmsmza9c8.pdf 162

This item appears in the following Collection(s)

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International

Search KOPS


Browse

My Account