MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
This addresses content moderation for social media platforms by improving detection of implicit harm in memes, representing an incremental advance with specific performance gains.
The paper tackles the problem of moderating harmful online memes that mask intent through humor or cultural symbolism, introducing MemeSense, an adaptive framework that combines visual and textual understanding with commonsense cues, achieving up to 35% higher semantic similarity and 9% improvement in BERTScore for non-textual memes compared to state-of-the-art methods.
Online memes are a powerful yet challenging medium for content moderation, often masking harmful intent behind humor, irony, or cultural symbolism. Conventional moderation systems "especially those relying on explicit text" frequently fail to recognize such subtle or implicit harm. We introduce MemeSense, an adaptive framework designed to generate socially grounded interventions for harmful memes by combining visual and textual understanding with curated, semantically aligned examples enriched with commonsense cues. This enables the model to detect nuanced complexed threats like misogyny, stereotyping, or vulgarity "even in memes lacking overt language". Across multiple benchmark datasets, MemeSense outperforms state-of-the-art methods, achieving up to 35% higher semantic similarity and 9% improvement in BERTScore for non-textual memes, and notable gains for text-rich memes as well. These results highlight MemeSense as a promising step toward safer, more context-aware AI systems for real-world content moderation. Code and data available at: https://github.com/sayantan11995/MemeSense