Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challenge

TL;DR

This study evaluates the effectiveness of state-of-the-art multimodal machine learning models in detecting hateful memes across platforms, revealing that visual features are more informative than text and highlighting the need for improved multimodal understanding.

Contribution

It provides a comprehensive analysis of current models' performance on large datasets and uncovers limitations in their ability to interpret cultural nuances in memes.

Findings

Visual features outperform textual content in hate detection.

Current models struggle with cross-platform generalization.

Multimodal models need enhancement to better understand cultural context.

Abstract

Internet memes have become a dominant method of communication; at the same time, however, they are also increasingly being used to advocate extremism and foster derogatory beliefs. Nonetheless, we do not have a firm understanding as to which perceptual aspects of memes cause this phenomenon. In this work, we assess the efficacy of current state-of-the-art multimodal machine learning models toward hateful meme detection, and in particular with respect to their generalizability across platforms. We use two benchmark datasets comprising 12,140 and 10,567 images from 4chan's "Politically Incorrect" board (/pol/) and Facebook's Hateful Memes Challenge dataset to train the competition's top-ranking machine learning models for the discovery of the most prominent features that distinguish viral hateful memes from benign ones. We conduct three experiments to determine the importance of multimodality on classification performance, the influential capacity of fringe Web communities on mainstream social platforms and vice versa, and the models' learning transferability on 4chan memes. Our experiments show that memes' image characteristics provide a greater wealth of information than its textual content. We also find that current systems developed for online detection of hate speech in memes necessitate further concentration on its visual elements to improve their interpretation of underlying cultural connotations, implying that multimodal models fail to adequately grasp the intricacies of hate speech in memes and generalize across social media platforms.