AMSA: Adaptive Multimodal Learning for Sentiment Analysis

Efficient recognition of emotions has attracted extensive research interest, which makes new applications in many fields possible, such as human-computer interaction, disease diagnosis, service robots, and so forth. Although existing work on sentiment analysis relying on sensors or unimodal methods performs well for simple contexts like business recommendation and facial expression recognition, it does far below expectations for complex scenes, such as sarcasm, disdain, and metaphors. In this article, we propose a novel two-stage multimodal learning framework, called AMSA, to adaptively learn correlation and complementarity between modalities for dynamic fusion, achieving more stable and precise sentiment analysis results. Specifically, a multiscale attention model with a slice positioning scheme is proposed to get stable quintuplets of sentiment in images, texts, and speeches in the first stage. Then a Transformer-based self-adaptive network is proposed to assign weights flexibly for multimodal fusion in the second stage and update the parameters of the loss function through compensation iteration. To quickly locate key areas for efficient affective computing, a patch-based selection scheme is proposed to iteratively remove redundant information through a novel loss function before fusion. Extensive experiments have been conducted on both machine weakly labeled and manually annotated datasets of self-made Video-SA, CMU-MOSEI, and CMU-MOSI. The results demonstrate the superiority of our approach through comparison with baselines.