Second Call for Participation
The spread of propagandistic messages relies on the use of psychological and rhetorical techniques. We have annotated a corpus of news articles with 18 techniques. This shared task aims at developing automatic models for the identification of such techniques in texts. Two subtasks are offered:
Subtask 1 (SI). Propaganda Identification.
Given a plain-text document, identify those specific fragments that contain a propaganda technique. This is a binary sequence tagging task.
Subtask 2 (TC). Propaganda Technique Labeling.
Given a text fragment identified as propaganda and its document context, identify the applied propaganda technique at hand. This is a 14-way multi-class classification problem.
The following propaganda techniques are considered:
* Loaded Language
* Name Calling, Labeling
* Exaggeration, Minimization
* Appeal to fear/prejudice
* Causal Oversimplification
* Appeal to Authority
* Black-and-White Fallacy
* Thought-terminating Cliches
* Bandwagon, Reductio ad Hitlerum
* Straw Men, Whataboutism, Red Herring
We believe the tasks would be appealing to various NLP communities, including researchers working on sentiment analysis, fact-checking, argumentation mining, tagging, and sequence models.
A live leaderboard is active and allows participants to track their progress on both tasks. All participants will be invited to submit a paper to the SemEval-2020 workshop, co-located with COLING 2020, Barcelona.
Shared task website: https://propaganda.qcri.org/semeval2020-task11
September 5th 2019 Registration opened
September 5th 2019 Release of the training and development sets.
February 18th 2020 Registration closes
February 19th 2020 Release of the test set for task SI
March 2nd 2020 Task SI test submissions site closes
March 3rd 2020 Release of the test set for task TC
March 11th 2020 Task TC test submissions site closes
April 17th 2020 Paper Submission deadline
June 10th 2020 Notification to authors
July 1st 2020 Camera ready papers due
September 13-14 2020 SemEval 2020 workshop at COLING
Giovanni Da San Martino, Qatar Computing Research Institute, HBKU
Alberto Barrón-Cedeño, Università di Bologna
Preslav Nakov, Qatar Computing Research Institute, HBKU
Henning Wachsmuth, Paderborn University
Rostislav Petrov, A Data Pro
For further details:
Shared task website: https://propaganda.qcri.org/semeval2020-task11 -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 22467 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200123/430110df/attachment.txt>