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.
We will provide 1 million articles labeled by the overall tendency of the publisher for training your algorithm. Upon registration we provide you with a trial dataset (may take up to 24 hours). We continuously clean the dataset (also based on your feedback) and will send you new versions as they come out.
When you registered, you will get remote access to a virtual machine (Windows or Linux) to deploy the task software in. Your software must be executable from the command line and not require Internet access during the evaluation period.
Note that you retain full copyrights of your software, but agree to grant us usage rights only for the purpose of the competition.
We provide a random baseline to illustrate the output of a submission and a term frequency extractor to illustrate how to read the dataset. For features, see the code from our ACL'18 publication for inspiration.
You will be able to self-evaluate your software using the TIRA service. You can find the user guide here. Main performance measure will be accuracy on a balanced set of articles. In addition, we will measure precision, recall, and F1-score for the hyperpartisan class.
For your convenience, we also provide the evaluation script that is used inside TIRA.
After the evaluation, participants are required to submit and review task description papers following the SemEval timeline.
To want to encourage developers to share their software so that everyone can profit from their work. We are thus excited to announce a grand prize of $1,000 to the best-performing submission that has its code published open source before the SemEval conference.