- Mawqif is the first Arabic dataset that can be used for target-specific stance detection.
- Stance detection aims to identify the position or perspective of a writer towards a specific topic or entity by analyzing his written text. The goal of this shared task is to propose models for detecting writers' stance (Favor, Against, or None) towards three topics (COVID-19 vaccine, digital transformation, and women empowerment).
- My best model achieves a macro-F1 of 75.46%, which shows that there is a room for improvement on this challenging task.
- For more information, please visit the shared task’s website
-
This dataset consists of 4,121 tweets in multi-dialectal Arabic. Each tweet is annotated with a stance toward one of three targets: “COVID-19 vaccine,” “digital transformation,” and “women empowerment.” In addition, it is annotated with sentiment and sarcasm polarities.
-
The following figure illustrates the labels’ distribution across all targets, and the distribution per target.
- You can check an interactive version of this visualisation here. You can click on visualization components to filter the data by target and by class.