Memotion Analysis through the Lens of Joint Embedding

TL;DR

This paper explores meme analysis using joint embedding techniques, aiming to encode memes for better understanding and detection of harmful content, with initial experiments showing marginally improved state-of-the-art results.

Contribution

It introduces the application of joint embedding methods to meme analysis, providing initial experimental results that suggest potential for improved automatic meme understanding.

Findings

Marginally improved state-of-the-art performance

Initial experiments demonstrate feasibility of joint embeddings for memes

Highlights potential for further research in meme content analysis

Abstract

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.