@inproceedings{wessel-horych-2024-beyond,
    title = "Beyond the Surface: Spurious Cues in Automatic Media Bias Detection",
    author = "Wessel, Martin  and
      Horych, Tom{\'a}{\v{s}}",
    editor = {Chakravarthi, Bharathi Raja  and
      B, Bharathi  and
      Buitelaar, Paul  and
      Durairaj, Thenmozhi  and
      Kov{\'a}cs, Gy{\"o}rgy  and
      Garc{\'i}a Cumbreras, Miguel {\'A}ngel},
    booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
    month = mar,
    year = "2024",
    address = "St. Julian's, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.ltedi-1.3/",
    pages = "21--30",
    abstract = "This study investigates the robustness and generalization of transformer-based models for automatic media bias detection. We explore the behavior of current bias classifiers by analyzing feature attributions and stress-testing with adversarial datasets. The findings reveal a disproportionate focus on rare but strongly connotated words, suggesting a rather superficial understanding of linguistic bias and challenges in contextual interpretation. This problem is further highlighted by inconsistent bias assessment when stress-tested with different entities and minorities. Enhancing automatic media bias detection models is critical to improving inclusivity in media, ensuring balanced and fair representation of diverse perspectives."
}