Multimodal Feature Extraction for Memes Sentiment Classification

TL;DR

This paper introduces a multimodal neural network approach for extracting features from memes to classify their sentiment, aiming to improve classification accuracy and generalizability.

Contribution

It proposes a novel multimodal feature extraction method using deep learning for meme sentiment classification, addressing the challenge of joint feature extraction from multiple modalities.

Findings

Effective multimodal feature extraction improves sentiment classification accuracy.

Deep learning approaches enhance generalizability and reduce overfitting.

The method outperforms traditional single-modality classifiers.

Abstract

In this study, we propose feature extraction for multimodal meme classification using Deep Learning approaches. A meme is usually a photo or video with text shared by the young generation on social media platforms that expresses a culturally relevant idea. Since they are an efficient way to express emotions and feelings, a good classifier that can classify the sentiment behind the meme is important. To make the learning process more efficient, reduce the likelihood of overfitting, and improve the generalizability of the model, one needs a good approach for joint feature extraction from all modalities. In this work, we proposed to use different multimodal neural network approaches for multimodal feature extraction and use the extracted features to train a classifier to identify the sentiment in a meme.