Text and target
A text in a supported language variety together with a target or proposition. The exact input schema will be announced.
AbjadNLP 2027 · Shared task
AbjadStanceEval 2027
Stance detection across Arabic language varieties
A proposed shared task on identifying whether a text supports, opposes or takes another stance towards a specified target. Arabic varieties are the initial focus; the final language coverage, labels and evaluation tracks are to be confirmed.
Proposed language coverage
Arabic (MSA and/or dialects)تحديد الموقف
Other Arabic-script languagesTo be confirmed
The Arabic phrase is illustrative, not a dataset example. Language coverage is provisional.
About the shared task
Identifying positions towards a target
Stance detection determines an author's position towards a particular topic, claim, person or policy. Unlike general sentiment analysis, stance is defined relative to a target and may differ from the emotional tone of a text.
Stance label
A prediction of the text's stance towards the target. Labels such as favour, against or neither are illustrative only; the official inventory is TBC.
Arabic varieties
Modern Standard Arabic and/or Arabic dialects are under consideration. The final dialect and MSA coverage will be confirmed by the organisers.
Additional languages
Other languages written in Arabic-derived scripts may be included, subject to data readiness and confirmation.
Data and evaluation
Dataset sources, training/development/test splits, target definitions, evaluation metrics, permissible external resources and submission requirements are not yet finalised. No particular scoring metric or dataset is being announced at this stage.
Taking part
Participation details
Registration, dataset release and evaluation instructions will be announced after the shared-task arrangements are confirmed.
This is a preliminary description. Refer to the workshop website for announcements and applicable policies.
Visit the AbjadNLP 2027 workshop page →- Languages
- Arabic (MSA/dialects TBC); others TBC
- Task tracks and labels
- To be confirmed
- Data access and licensing
- To be announced
- Evaluation metrics
- To be confirmed
- Registration and submissions
- To be announced
- Shared-task dates
- To be announced
The team
Shared-task organisers
The previous edition's organising team is shown below; the 2027 team is subject to confirmation.
- Saad EzziniKing Fahd University of Petroleum & Minerals
- Irfan AhmedKing Fahd University of Petroleum & Minerals
- Salmane ChafikMohammed VI Polytechnic University
- Shadi AbudalfaKing Fahd University of Petroleum & Minerals
- Mo El-HajVinUniversity
- Ahmed AbdelaliHUMAIN
- Mustafa JarrarHamad Bin Khalifa University / Birzeit University
- Nadir DurraniHamad Bin Khalifa University
- Hassan SajjadDalhousie University
- Farah AdeebaUniversity of Massachusetts Amherst