# RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification

arXiv: https://arxiv.org/abs/2310.09596 · HTML: https://mlsanity.com/paper/2310.09596/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation](https://mlsanity.com/paper/2108.01682/) (2021)
- [Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2204.07955/) (2022)

## Built on by (most cited first, 2 of 2)

- [Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2504.15848/) (2025)
- [Target-oriented Multimodal Sentiment Classification with Counterfactual-enhanced Debiasing](https://mlsanity.com/paper/2509.09160/) (2025)

## Abstract (arXiv)

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.