@inproceedings{amason-etal-2019-harvey,
    title = "Harvey Mudd College at {S}em{E}val-2019 Task 4: The {D}.{X}. Beaumont Hyperpartisan News Detector",
    author = "Amason, Evan  and
      Palanker, Jake  and
      Shen, Mary Clare  and
      Medero, Julie",
    editor = "May, Jonathan  and
      Shutova, Ekaterina  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Apidianaki, Marianna  and
      Mohammad, Saif M.",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/S19-2166/",
    doi = "10.18653/v1/S19-2166",
    pages = "967--970",
    abstract = "We use the 600 hand-labelled articles from SemEval Task 4 to hand-tune a classifier with 3000 features for the Hyperpartisan News Detection task. Our final system uses features based on bag-of-words (BoW), analysis of the article title, language complexity, and simple sentiment analysis in a naive Bayes classifier. We trained our final system on the 600,000 articles labelled by publisher. Our final system has an accuracy of 0.653 on the hand-labeled test set. The most effective features are the Automated Readability Index and the presence of certain words in the title. This suggests that hyperpartisan writing uses a distinct writing style, especially in the title."
}