Nullpointer at ArAIEval Shared Task: Arabic Propagandist Technique Detection with Token-to-Word Mapping in Sequence Tagging
This work addresses propaganda detection in Arabic for social media and news, but it is incremental as it builds on existing models and shared task benchmarks.
The paper tackled propaganda technique detection in Arabic text by fine-tuning AraBERT v2 with a neural network classifier for sequence tagging, achieving a score of 25.41 (4th place) and later improving to 26.68 through post-submission enhancements.
This paper investigates the optimization of propaganda technique detection in Arabic text, including tweets \& news paragraphs, from ArAIEval shared task 1. Our approach involves fine-tuning the AraBERT v2 model with a neural network classifier for sequence tagging. Experimental results show relying on the first token of the word for technique prediction produces the best performance. In addition, incorporating genre information as a feature further enhances the model's performance. Our system achieved a score of 25.41, placing us 4$^{th}$ on the leaderboard. Subsequent post-submission improvements further raised our score to 26.68.