AI learns to spot propaganda in memes across languages
Researchers developed a machine-learning system that identifies persuasion techniques embedded in meme text across multiple languages, ranking second in two languages at a major competition. The breakthrough matters for social media platforms, advertisers, and misinformation researchers racing to detect manipulative content at scale.
Originaltitel: RDproj at SemEval-2024 Task 4: An Ensemble Learning Approach for Multilingual Detection of Persuasion Techniques in Memes
<p>This paper introduces our bagging-based ensemble learning approach for the SemEval-2024 Task 4 Subtask 1, focusing on multilingual persuasion detection within meme texts. This task aims to identify persuasion techniques employed within meme texts, which is a hierarchical multilabel classification task. The given text may apply multiple techniques, and persuasion techniques have a hierarchical structure. However, only a few prior persuasion detection systems have utilized the hierarchical structure of persuasion techniques. In that case, we designed a multilingual bagging-based ensemble approach, incorporating a soft voting ensemble strategy to effectively exploit persuasion techniques' hierarchical structure. Our methodology achieved the second position in Bulgarian and North Macedonian, fifth in Arabic, and eleventh in English.</p>