Quantum-Classical Sentiment Analysis

TL;DR

This paper explores a hybrid quantum-classical approach to sentiment analysis, comparing its performance and convergence speed with classical and Transformer models, and proposes an algorithm to improve quantum processing efficiency.

Contribution

It introduces a novel algebraic decomposition algorithm for QUBO models to enhance quantum processing time in sentiment analysis tasks.

Findings

HCQC converges faster than classical models but has lower accuracy than Transformers.

A new algebraic decomposition algorithm improves quantum resource allocation.

The study identifies a bottleneck in the HCQC architecture related to D-Wave properties.

Abstract

In this study, we initially investigate the application of a hybrid classical-quantum classifier (HCQC) for sentiment analysis, comparing its performance against the classical CPLEX classifier and the Transformer architecture. Our findings indicate that while the HCQC underperforms relative to the Transformer in terms of classification accuracy, but it requires significantly less time to converge to a reasonably good approximate solution. This experiment also reveals a critical bottleneck in the HCQC, whose architecture is partially undisclosed by the D-Wave property. To address this limitation, we propose a novel algorithm based on the algebraic decomposition of QUBO models, which enhances the time the quantum processing unit can allocate to problem-solving tasks.