Deep Learning-Based Multimodal Sentiment Analysis

Zijian Wang

2024

Abstract

The area of natural language processing has a substantial amount of research that focuses on multimodal sentiment analysis. It aims at how people express their feelings through different types of speech and can be used in many areas, such as e-commerce, film and TV reviews, and more. With the advent of technologies like as machine learning, deep learning, and others, significant progress has been achieved in the area of multimodal sentiment analysis. First, this paper introduces multimodal emotion analysis, and then divides emotion analysis into narrative and interactivity according to the presence or absence of dialogue. The characteristics and distinctions of these two sentiment analysis approaches are then introduced, with respect to data, algorithm, and application, by analyzing pertinent recent domestic and international research. Lastly, this work addresses the future directions for research as well as the current drawbacks of multimodal sentiment analysis. With that said, this paper provides a reference for sentiment analysis researchers and outlines future research in this dynamic topic.

Paper Citation

in Harvard Style

Wang Z. (2024). Deep Learning-Based Multimodal Sentiment Analysis. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 356-363. DOI: 10.5220/0012842200004547

in Bibtex Style

@conference{icdse24,
author={Zijian Wang},
title={Deep Learning-Based Multimodal Sentiment Analysis},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={356-363},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012842200004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Deep Learning-Based Multimodal Sentiment Analysis
SN - 978-989-758-690-3
AU - Wang Z.
PY - 2024
SP - 356
EP - 363
DO - 10.5220/0012842200004547
PB - SciTePress