# Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt

arXiv: https://arxiv.org/abs/2305.10169 · HTML: https://mlsanity.com/paper/2305.10169/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2023.

## Built on by (most cited first, 9 of 9)

- [Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey](https://mlsanity.com/paper/2406.08068/) (2024)
- [Recent Advances in Multimodal Affective Computing: An NLP Perspective](https://mlsanity.com/paper/2409.07388/) (2024)
- [UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause](https://mlsanity.com/paper/2404.00403/) (2024)
- [CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval](https://mlsanity.com/paper/2412.13071/) (2024)
- [Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales](https://mlsanity.com/paper/2505.14499/) (2025)
- [Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model](https://mlsanity.com/paper/2410.14225/) (2024)
- [AdaptiSent: Context-Aware Adaptive Attention for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2507.12695/) (2025)
- [Utilizing Large Language Models for Event Deconstruction to Enhance Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2410.14150/) (2024)
- [Data Uncertainty-Aware Learning for Multimodal Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2412.01249/) (2024)

## Abstract (arXiv)

We have witnessed the rapid proliferation of multimodal data on numerous social media platforms. Conventional studies typically require massive labeled data to train models for Multimodal Aspect-Based Sentiment Analysis (MABSA). However, collecting and annotating fine-grained multimodal data for MABSA is tough. To alleviate the above issue, we perform three MABSA-related tasks with quite a small number of labeled multimodal samples. We first build diverse and comprehensive multimodal few-shot datasets according to the data distribution. To capture the specific prompt for each aspect term in a few-shot scenario, we propose a novel Generative Multimodal Prompt (GMP) model for MABSA, which includes the Multimodal Encoder module and the N-Stream Decoders module. We further introduce a subtask to predict the number of aspect terms in each instance to construct the multimodal prompt. Extensive experiments on two datasets demonstrate that our approach outperforms strong baselines on two MABSA-related tasks in the few-shot setting.