Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting

TL;DR

This paper introduces a novel Chain-of-Thought prompting method using a Unified Meaning Representation to enhance zero-shot Aspect-Category Sentiment Analysis with large language models, showing promising but model-dependent results.

Contribution

It proposes a UMR-based CoT prompting technique for zero-shot ACSA, addressing data scarcity issues and exploring model performance variations.

Findings

UMR-based approach shows promise with mid-sized models

Performance may depend on the specific language model used

Further research needed for smaller models and generalisability

Abstract

Aspect-Category Sentiment Analysis (ACSA) provides granular insights by identifying specific themes within reviews and their associated sentiment. While supervised learning approaches dominate this field, the scarcity and high cost of annotated data for new domains present significant barriers. We argue that leveraging large language models (LLMs) in a zero-shot setting is a practical alternative where resources for data annotation are limited. In this work, we propose a novel Chain-of-Thought (CoT) prompting technique that utilises an intermediate Unified Meaning Representation (UMR) to structure the reasoning process for the ACSA task. We evaluate this UMR-based approach against a standard CoT baseline across three models (Qwen3-4B, Qwen3-8B, and Gemini-2.5-Pro) and four diverse datasets. Our findings suggest that UMR effectiveness may be model-dependent. Whilst preliminary results indicate comparable performance for mid-sized models such as Qwen3-8B, these observations warrant further investigation, particularly regarding the potential applicability to smaller model architectures. Further research is required to establish the generalisability of these findings across different model scales.