Frank at ArAIEval Shared Task: Arabic Persuasion and Disinformation: The Power of Pretrained Models
Document Type
Conference Proceeding
Publication Title
ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings
Abstract
In this work, we present our systems developed for “ARAIEVAL” shared task of ArabicNLP 2023 (Hasanain et al., 2023a). We used an mBERT transformer for Subtask 1A, which targets persuasion in Arabic tweets, and we used the MARBERT transformer for Subtask 2A to identify disinformation in Arabic tweets. Our persuasion detection system achieved micro-F1 of 0.745 by surpassing the baseline by 13.2%, and registered a macro-F1 of 0.717 based on leaderboard scores. Similarly, our disinformation system recorded a micro-F1 of 0.816, besting the naïve majority by 6.7%, with a macroF1 of 0.637. Furthermore, we present our preliminary results on a variety of pre-trained models. In terms of overall ranking, our systems placed 7th out of 16 and 12th out of 17 teams for Subtasks 1A and 2A, respectively.
First Page
583
Last Page
588
Publication Date
1-1-2023
Recommended Citation
D. Azizov et al., "Frank at ArAIEval Shared Task: Arabic Persuasion and Disinformation: The Power of Pretrained Models," ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings, pp. 583 - 588, Jan 2023.