IUSTNLPLAB at SemEval-2024 Task 4: Multilingual Detection of Persuasion Techniques in Memes

Download PDF
Open Webpage

Mohammad Osoolian, Erfan Moosavi Monazzah, Sauleh Eetemadi

Published: 01 Jan 2024, Last Modified: 21 May 2025SemEval@NAACL 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: This paper outlines our approach to SemEval-2024 Task 4: Multilingual Detection of Persuasion Techniques in Memes, specifically addressing subtask 1. The study focuses on model fine-tuning using language models, including BERT, GPT-2, and RoBERTa, with the experiment results demonstrating optimal performance with GPT-2. Our system submission achieved a competitive ranking of 17th out of 33 teams in subtask 1, showcasing the effectiveness of the employed methodology in the context of persuasive technique identification within meme texts.