# Multimodal prototypical network for interpretable sentiment classification

## TL;DR

This paper introduces a new interpretable model for sentiment analysis that handles multiple data types from videos and explains its decisions over time.

## Contribution

The novel contribution is extending prototype networks to handle multimodal and temporal data for interpretable sentiment classification.

## Key findings

- MMPNet outperforms existing methods by 2.9% on CMU-MOSI and 1.6% on CMU-MOSEI in accuracy.
- The model provides better interpretability by identifying temporal and modality-level feature contributions.

## Abstract

Recent advances in sentiment analysis have primarily focused on fusing multimodal information from video data, including visual, acoustic, and textual features, across temporal sequences. While great effort has been made to integrate or fuse information across modalities, less is known about the extent to which temporal segments contribute to model decisions. In addition, current interpretable methods, such as prototype networks, are primarily designed for uni-modal analysis and fail to handle the complex interactions between multiple modalities and temporal dependencies inherent in video data. To address the challenges, we propose MultiModal Prototypical Networks (MMPNet), which extends prototype-based interpretability to multimodal sentiment classification. Specifically, MMPNet can identify contributions of time-level features and leverage them to explain why a particular prediction was made, while also helping to find the relative importance of modality-level features. Experimental results show that MMPNet outperforms existing methods by 2.9% and 1.6% in accuracy on CMU-MOSI and CMU-MOSEI respectively, and achieves better interpretability.