On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning

TL;DR

This paper introduces a multimodal contrastive learning framework using CLIP to analyze and track the evolution of hateful memes, aiding moderation efforts by identifying new variants and their semantic relationships.

Contribution

The paper presents a novel framework leveraging CLIP's semantic regularities to systematically study the creation and variation of hateful memes, especially antisemitic ones like the Happy Merchant.

Findings

Identified 3.3K variants of the Happy Merchant meme.

Linked meme variants to specific countries, persons, or organizations.

Demonstrated the framework's potential to assist human moderators in detecting new hateful meme variants.

Abstract

The dissemination of hateful memes online has adverse effects on social media platforms and the real world. Detecting hateful memes is challenging, one of the reasons being the evolutionary nature of memes; new hateful memes can emerge by fusing hateful connotations with other cultural ideas or symbols. In this paper, we propose a framework that leverages multimodal contrastive learning models, in particular OpenAI's CLIP, to identify targets of hateful content and systematically investigate the evolution of hateful memes. We find that semantic regularities exist in CLIP-generated embeddings that describe semantic relationships within the same modality (images) or across modalities (images and text). Leveraging this property, we study how hateful memes are created by combining visual elements from multiple images or fusing textual information with a hateful image. We demonstrate the capabilities of our framework for analyzing the evolution of hateful memes by focusing on antisemitic memes, particularly the Happy Merchant meme. Using our framework on a dataset extracted from 4chan, we find 3.3K variants of the Happy Merchant meme, with some linked to specific countries, persons, or organizations. We envision that our framework can be used to aid human moderators by flagging new variants of hateful memes so that moderators can manually verify them and mitigate the problem of hateful content online.