MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification
This work addresses the problem of multimodal meme classification for researchers and practitioners in social media analysis, though it is incremental as it builds on existing CLIP models with a new dataset and framework.
The study tackled multimodal classification of text-embedded images by expanding analysis to multiple linguistic aspects like hate, targets, stance, and humor, introducing a novel dataset PrideMM with 5,063 images and proposing MemeCLIP, which achieved superior performance on two real-world datasets compared to previous frameworks.
The complexity of text-embedded images presents a formidable challenge in machine learning given the need for multimodal understanding of multiple aspects of expression conveyed by them. While previous research in multimodal analysis has primarily focused on singular aspects such as hate speech and its subclasses, this study expands this focus to encompass multiple aspects of linguistics: hate, targets of hate, stance, and humor. We introduce a novel dataset PrideMM comprising 5,063 text-embedded images associated with the LGBTQ+ Pride movement, thereby addressing a serious gap in existing resources. We conduct extensive experimentation on PrideMM by using unimodal and multimodal baseline methods to establish benchmarks for each task. Additionally, we propose a novel framework MemeCLIP for efficient downstream learning while preserving the knowledge of the pre-trained CLIP model. The results of our experiments show that MemeCLIP achieves superior performance compared to previously proposed frameworks on two real-world datasets. We further compare the performance of MemeCLIP and zero-shot GPT-4 on the hate classification task. Finally, we discuss the shortcomings of our model by qualitatively analyzing misclassified samples. Our code and dataset are publicly available at: https://github.com/SiddhantBikram/MemeCLIP.