/semeval2019-hyperpartisan-news

Our submission to the SemEval2019 shared task on Hyperpartisan News Detection.

Primary LanguagePython

SemEval2019 Task 4 - Hyperpartisan News Detection

Task

Given a news article text, decide whether it follows a hyperpartisan argumentation, i.e., whether it exhibits blind, prejudiced, or unreasoning allegiance to one party, faction, cause, or person.

System's Performance

Model Accuracy Precision Recall F1
Random Forest (Official) 71.7 80.6 57.0 66.8
Gradient Boosted Trees (Best) 72.9 78.1 63.7 70.2
Baseline 46.2 46.0 44.3 45.1

Team Members

  • AndrĂ© Cruz
  • Gil Rocha
  • Rui Sousa-Silva
  • Henrique Lopes Cardoso

Citation

@inproceedings{cruz-etal-2019-team,
    title = "Team Fernando-Pessa at {S}em{E}val-2019 Task 4: Back to Basics in Hyperpartisan News Detection",
    author = "Cruz, Andr{\'e}  and
      Rocha, Gil  and
      Sousa-Silva, Rui  and
      Lopes Cardoso, Henrique",
    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://www.aclweb.org/anthology/S19-2173",
    doi = "10.18653/v1/S19-2173",
    pages = "999--1003",
}