Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis

TL;DR

This paper introduces a multimodal sentiment analysis approach combining novel feature extraction, advanced fusion techniques, and data augmentation to improve accuracy across humor, reaction, and stress detection challenges.

Contribution

It presents new multimodal features, fusion methods, and data augmentation strategies that enhance sentiment prediction accuracy and reliability.

Findings

Achieved high AUC score of 0.8932 in humor detection

Outperformed all participants in reaction sub-challenge with Pearson's 0.3879

Surpassed baseline in stress detection with combined score of 0.5151

Abstract

In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges. The MuSe 2022 focuses on humor detection, emotional reactions and multimodal emotional stress utilizing different modalities and data sets. In our work, different kinds of multimodal features are extracted, including acoustic, visual, text and biological features. These features are fused by TEMMA and GRU with self-attention mechanism frameworks. In this paper, 1) several new audio features, facial expression features and paragraph-level text embeddings are extracted for accuracy improvement. 2) we substantially improve the accuracy and reliability of multimodal sentiment prediction by mining and blending the multimodal features. 3) effective data augmentation strategies are applied in model training to alleviate the problem of sample imbalance and prevent the model from learning biased subject characters. For the MuSe-Humor sub-challenge, our model obtains the AUC score of 0.8932. For the MuSe-Reaction sub-challenge, the Pearson's Correlations Coefficient of our approach on the test set is 0.3879, which outperforms all other participants. For the MuSe-Stress sub-challenge, our approach outperforms the baseline in both arousal and valence on the test dataset, reaching a final combined result of 0.5151.