RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification
This work addresses the problem of inefficient multimodal integration in sentiment analysis for researchers, but it is incremental as it primarily analyzes existing limitations without introducing new methods.
The study tackled the performance bottleneck in Target-oriented Multimodal Sentiment Classification (TMSC) by empirically evaluating datasets and models, finding that current systems rely heavily on text, with most target sentiments determinable from text alone, and suggesting directions for model design and dataset construction.
Recently, Target-oriented Multimodal Sentiment Classification (TMSC) has gained significant attention among scholars. However, current multimodal models have reached a performance bottleneck. To investigate the causes of this problem, we perform extensive empirical evaluation and in-depth analysis of the datasets to answer the following questions: Q1: Are the modalities equally important for TMSC? Q2: Which multimodal fusion modules are more effective? Q3: Do existing datasets adequately support the research? Our experiments and analyses reveal that the current TMSC systems primarily rely on the textual modality, as most of targets' sentiments can be determined solely by text. Consequently, we point out several directions to work on for the TMSC task in terms of model design and dataset construction. The code and data can be found in https://github.com/Junjie-Ye/RethinkingTMSC.