QD-MSA : A quantum distributed tensor network framework for multimodal sentiment analysis

Abstract

Multimodal sentiment analysis, which integrates data types such as audio, text, and images, is increasingly vital for understanding emotional content in the era of social media and short video platforms. Quantum computing, with its inherent characteristics like superposition and entanglement, is conceptually well-suited for multimodal learning, particularly for modal fusion. However, current quantum computers face limitations, such as a restricted number of usable qubits, hindering their ability to surpass classical computing (quantum supremacy). In this work, we propose QD-MSA, a quantum distributed multimodal sentiment analysis framework, which is the first to apply quantum circuit splitting techniques to multimodal sentiment analysis, reducing qubit usage from $n$ to $n/2+1$. This advancement enables the execution of more complex quantum programs on Noisy Intermediate-Scale Quantum (NISQ) devices by partially overcoming qubit scarcity. Additionally, QD-MSA contains a novel workflow that integrates our model into quantum computer clusters, significantly enhancing computational performance and unlocking the potential of NISQ-era quantum computers. By combining classical neural networks for feature extraction with quantum models for feature fusion, our approach conserves quantum resources while achieving superior performance. Experimental evaluations on the CMU-MOSEI and CMU-MOSI datasets demonstrate that our model achieves comparable or superior performance to deep learning-based methods, with notable improvements in key metrics. Furthermore, our work represents the first successful integration of quantum computing principles into multimodal sentiment analysis, with experiments confirming that the proposed model significantly outperforms classical approaches relying solely on quantum-inspired strategies. These contributions establish a scalable and efficient framework for multimodal sentiment analysis, leveraging both classical and quantum computing paradigms to advance the field.