2016/09/16 by Haohan Wang, Wang, Haohan, Aaksha Meghawat +5 · 2 citations
Computer Science · Psychology · #Computation and Language (cs.CL) #Emotion and Mood Recognition #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Sentiment Analysis and Opinion Mining #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1609.05244
openalex publication_date 2016/09/16 · openalex created_date 2017/04/28 · openalex updated_date 2026/07/28
Multimodal sentiment analysis is drawing an increasing amount of attention these days. It enables mining of opinions in video reviews which are now available aplenty on online platforms. However, multimodal sentiment analysis has only a few high-quality data sets annotated for training machine learning algorithms. These limited resources restrict the generalizability of models, where, for example, the unique characteristics of a few speakers (e.g., wearing glasses) may become a confounding factor for the sentiment classification task. In this paper, we propose a Select-Additive Learning (SAL) procedure that improves the generalizability of trained neural networks for multimodal sentiment analysis. In our experiments, we show that our SAL approach improves prediction accuracy significantly in all three modalities (verbal, acoustic, visual), as well as in their fusion. Our results show that SAL, even when trained on one dataset, achieves good generalization across two new test datasets.