English

Benchmarking Multimodal Sentiment Analysis

Multimedia 2017-08-01 v1 Computation and Language

Abstract

We propose a framework for multimodal sentiment analysis and emotion recognition using convolutional neural network-based feature extraction from text and visual modalities. We obtain a performance improvement of 10% over the state of the art by combining visual, text and audio features. We also discuss some major issues frequently ignored in multimodal sentiment analysis research: the role of speaker-independent models, importance of the modalities and generalizability. The paper thus serve as a new benchmark for further research in multimodal sentiment analysis and also demonstrates the different facets of analysis to be considered while performing such tasks.

Keywords

Cite

@article{arxiv.1707.09538,
  title  = {Benchmarking Multimodal Sentiment Analysis},
  author = {Erik Cambria and Devamanyu Hazarika and Soujanya Poria and Amir Hussain and R. B. V. Subramaanyam},
  journal= {arXiv preprint arXiv:1707.09538},
  year   = {2017}
}

Comments

Accepted in CICLing 2017

R2 v1 2026-06-22T21:01:20.815Z