Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation
This work addresses the challenge of automatic moderation of hate speech in memes to reduce harmful societal impact, but it is incremental as it builds on existing detection methods by incorporating visual data.
The paper tackles the problem of detecting hate speech in Internet memes by using visual information, unlike prior linguistic-focused approaches, and finds that visual modality is more informative, with experiments on a dataset of 5,020 memes showing the model can learn to detect some memes but the task remains unsolved with their simple architecture.
This work addresses the challenge of hate speech detection in Internet memes, and attempts using visual information to automatically detect hate speech, unlike any previous work of our knowledge. Memes are pixel-based multimedia documents that contain photos or illustrations together with phrases which, when combined, usually adopt a funny meaning. However, hate memes are also used to spread hate through social networks, so their automatic detection would help reduce their harmful societal impact. Our results indicate that the model can learn to detect some of the memes, but that the task is far from being solved with this simple architecture. While previous work focuses on linguistic hate speech, our experiments indicate how the visual modality can be much more informative for hate speech detection than the linguistic one in memes. In our experiments, we built a dataset of 5,020 memes to train and evaluate a multi-layer perceptron over the visual and language representations, whether independently or fused. The source code and mode and models are available https://github.com/imatge-upc/hate-speech-detection .