Clustering Internet Memes Through Template Matching and Multi-Dimensional Similarity

2025-04-30

AI Summary

Meme clustering on the Internet faces challenges in modeling semantic similarity due to multimodality, cultural dependency, and dynamic evolution; existing approaches largely rely on predefined databases, neglecting semantic diversity. This paper proposes the first database-free, template-matching–based adaptive clustering framework for memes. It jointly models four-dimensional semantic similarities—structural, visual, textual, and identity-related—and integrates local-global similarity metrics with unsupervised clustering. Crucially, the method eliminates dependence on annotated data or fixed template repositories, enabling semantically coherent, cross-cultural, and cross-platform meme clustering. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art methods, yielding clusters that are more cohesive, interpretable, and aligned with human intuition. The complete implementation is publicly available.

Technology Category

• Machine Learning: Clustering
• Natural Language Processing: Lexical Semantics and Morphology
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Meme clustering is critical for toxicity detection, virality modeling, and typing, but it has received little attention in previous research. Clustering similar Internet memes is challenging due to their multimodality, cultural context, and adaptability. Existing approaches rely on databases, overlook semantics, and struggle to handle diverse dimensions of similarity. This paper introduces a novel method that uses template-based matching with multi-dimensional similarity features, thus eliminating the need for predefined databases and supporting adaptive matching. Memes are clustered using local and global features across similarity categories such as form, visual content, text, and identity. Our combined approach outperforms existing clustering methods, producing more consistent and coherent clusters, while similarity-based feature sets enable adaptability and align with human intuition. We make all supporting code publicly available to support subsequent research. Code: https://github.com/tygobl/meme-clustering

Problem

• Clustering Internet memes for toxicity detection and virality modeling
• Overcoming multimodality and cultural context challenges in meme clustering
• Improving clustering accuracy with template-based multi-dimensional similarity features

Innovation

• Template-based matching for meme clustering
• Multi-dimensional similarity features integration
• No need for predefined meme databases