Sentiment Analysis on Memes: A Review

Abstract

This review explores the field of Sentiment Analysis on Memes, examining the methodologies employed to analyse the emotions expressed in widely shared online images. We discuss the various architectures used in sentiment analysis, review existing datasets and highlight shared tasks that facilitate model evaluation. The review also addresses the challenges specific to this domain, such as the interpretation of humour and sarcasm, which add complexity to sentiment analysis in the context of memes. A key focus of this review is the need for novel datasets that better capture the unique nature of memes, particularly those that blend text and images with cultural and emotional nuances. Existing benchmark datasets often fall short in representing the diversity of meme formats and regional variations, highlighting the necessity for more comprehensive datasets. Looking forward, we anticipate advancements in analytical methodologies and the development of such specialised datasets, which would significantly enhance the accuracy and depth of sentiment analysis models. This review serves as a comprehensive resource for researchers and practitioners interested in advancing the study of sentiment analysis in the evolving field of memes.