Multimodal and Explainable Internet Meme Classification

TL;DR

This paper introduces a modular, multimodal, and explainable approach to Internet meme classification, enhancing content moderation by explicitly considering meme semantics and context, and providing interpretability through example- and prototype-based reasoning.

Contribution

It presents a novel explainable architecture for meme understanding that combines multimodal models with reasoning methods, addressing limitations of black-box approaches.

Findings

Multimodal models outperform unimodal ones in detecting harmful memes.

Prototype-based reasoning provides better interpretability than example-based methods.

The system effectively identifies hate speech and misogyny in memes.

Abstract

In the current context where online platforms have been effectively weaponized in a variety of geo-political events and social issues, Internet memes make fair content moderation at scale even more difficult. Existing work on meme classification and tracking has focused on black-box methods that do not explicitly consider the semantics of the memes or the context of their creation. In this paper, we pursue a modular and explainable architecture for Internet meme understanding. We design and implement multimodal classification methods that perform example- and prototype-based reasoning over training cases, while leveraging both textual and visual SOTA models to represent the individual cases. We study the relevance of our modular and explainable models in detecting harmful memes on two existing tasks: Hate Speech Detection and Misogyny Classification. We compare the performance between example- and prototype-based methods, and between text, vision, and multimodal models, across different categories of harmfulness (e.g., stereotype and objectification). We devise a user-friendly interface that facilitates the comparative analysis of examples retrieved by all of our models for any given meme, informing the community about the strengths and limitations of these explainable methods.