ArAIEval shared task at WANLP 2023! (co-located with EMNLP 2023)

Shared Task On Propaganda And Disinformation Detection In Arabic (co-located with EMNLP 2023)

You are invited to participate ArAIEval shared task on (i) persuasion technique, and (ii) disinformation detection, in Arabic, which will held with the First Arabic Natural Language Processing Conference (WANLP 2023) co-located this with the EMNLP2023 Conference in Singapore (6-10 Dec, 2023). You can find detailed information here: https://araieval.gitlab.io/.

Tasks

• Task 1: Persuasion Technique Detection: Given a multigenre (tweet and news paragraph) text snippet, identify whether it contains content with persuasion technique in a binary or multilabel classification settings.
• Task 2: Disinformation Detection Definition: Given only the “text” of a tweet, classify binary and/or fine-grained disinformation categories.

Website: https://araieval.gitlab.io/
Dataset and relevant scripts:
The datasets are hosted on the Gitlab repository: https://gitlab.com/araieval/wanlp2023_araieval/

Important Dates

• 13 July 2023: Started registration on codalab and beginning of the development cycle
• 12 August 2023: Beginning of the evaluation cycle (test sets release and run submission)
• 15 August 2023 23:59 AOE: End of the evaluation cycle (run submission)
• 29 August 2023: Deadline for the submission of working notes
• 12 October 2023: Notification of acceptance of working notes
• 20 October 2023: Deadline for submission of camera-ready working notes
• 7 December 2023: WANLP Conference (colocated with EMNLP-2023)

Organizers

• Firoj Alam, Qatar Computing Research Institute, HBKU
• Hamdy Mubarak, Qatar Computing Research Institute, HBKU
• Maram Hasanain, Qatar Computing Research Institute, HBKU
• Samir Abdaljalil, Qatar Computing Research Institute, HBKU
• Wajdi Zaghouani, HBKU
• Preslav Nakov, Mohamed bin Zayed University of Artificial Intelligence
• Giovanni Da San Martino, University of Padova
• Abdelhakim Freihat, University of Trento