A Template Is All You Meme
This work addresses a gap in computational meme analysis for researchers and practitioners, though it is incremental as it builds on existing meme processing methods.
The paper tackled the problem of analyzing templatic memes by creating a knowledge base of over 5,200 templates and 54,000 instances, and introduced TSplit to reorganize datasets, achieving state-of-the-art performance across all evaluated datasets.
Templatic memes, characterized by a semantic structure adaptable to the creator's intent, represent a significant yet underexplored area within meme processing literature. With the goal of establishing a new direction for computational meme analysis, here we create a knowledge base composed of more than 5,200 meme templates, information about them, and 54,000 examples of template instances (templatic memes). To investigate the semantic signal of meme templates, we show that we can match memes in datasets to base templates contained in our knowledge base with a distance-based lookup. To demonstrate the power of meme templates, we create TSplit, a method to reorganize datasets, where a template or templatic instance can only appear in either the training or test split. Our re-split datasets enhance general meme knowledge and improve sample efficiency, leading to more robust models. Our examination of meme templates results in state-of-the-art performance for every dataset we consider, paving the way for analysis grounded in templateness.