Internet Memes remain a challenging form of user-generated content for automated sentiment classification. The availability of labelled memes is a barrier to developing sentiment classifiers of multimodal memes. To address the shortage of labelled memes, we propose to supplement the training of a multimodal meme classifier with unimodal (image-only and text-only) data. In this work, we present a novel variant of supervised intermediate training that uses relatively abundant sentiment-labelled unimodal data. Our results show a statistically significant performance improvement from the incorporation of unimodal text data. Furthermore, we show that the training set of labelled memes can be reduced by 40% without reducing the performance of the downstream model.
@article{arxiv.2308.00528,
title = {Unimodal Intermediate Training for Multimodal Meme Sentiment Classification},
author = {Muzhaffar Hazman and Susan McKeever and Josephine Griffith},
journal= {arXiv preprint arXiv:2308.00528},
year = {2025}
}