Memotion Analysis through the Lens of Joint Embedding
This addresses the challenge of meme analysis for social media platforms, but it is incremental as it builds on existing joint embedding methods.
The paper tackles the problem of automatically analyzing memes, which can spread hate and fake information, by using joint embeddings to encode multi-modal data, and reports initial experiments that marginally yield state-of-the-art results.
Joint embedding (JE) is a way to encode multi-modal data into a vector space where text remains as the grounding key and other modalities like image are to be anchored with such keys. Meme is typically an image with embedded text onto it. Although, memes are commonly used for fun, they could also be used to spread hate and fake information. That along with its growing ubiquity over several social platforms has caused automatic analysis of memes to become a widespread topic of research. In this paper, we report our initial experiments on Memotion Analysis problem through joint embeddings. Results are marginally yielding SOTA.