SemEval 2019 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.

Data

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.

Registration

Register yourself or your team here. This task will use the PAN mailing list for communication, so please sign up there to ask questions to us or other participants. If you have specific requests, please write to the organizer's mailing list.

Submission (December 2018)

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.

Evaluation (January 2019)

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.

Grand Prize (Summer 2019)

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.

Johannes
Kiesel

Bauhaus-Universität Weimar

Martin
Potthast

Leipzig University

Maria
Mestre

Factmata Ltd.

Rishabh
Shukla

Factmata Ltd.

Benno
Stein

Bauhaus-Universität Weimar

Emmanuel
Vincent

Factmata Ltd.

Payam
Adineh

Bauhaus-Universität Weimar