RD-MCSA: A Multi-Class Sentiment Analysis Approach Integrating In-Context Classification Rationales and Demonstrations

ACL ARR 2025 May Submission7518 Authors

Abstract:

This paper addresses the important yet underexplored task of multi-class sentiment analysis (MCSA), which remains challenging due to subtle semantic differences between adjacent sentiment categories and the scarcity of high-quality annotated data.

To tackle these challenges, RD-MCSA (Rationales and Demonstrations-based Multi-Class Sentiment Analysis) is proposed as an In-Context Learning (ICL) framework designed to improve MCSA performance under limited supervision by integrating classification rationales and adaptively selected demonstrations.

First, semantically grounded classification rationales are generated from a representative, class-balanced subset of annotated samples selected using a tailored balanced coreset algorithm.

These rationales are then paired with demonstrations selected via a similarity-based mechanism powered by a multi-kernel Gaussian process (MK-GP), enabling large language models (LLMs) to better capture fine-grained sentiment distinctions.

Experiments on five benchmark sentiment datasets show that RD-MCSA consistently outperforms both supervised baselines and standard ICL methods across various evaluation metrics.

Paper Type: Long

Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Research Area Keywords: stance detection; applications;

Contribution Types: Reproduction study, Approaches to low-resource settings, Publicly available software and/or pre-trained models, Data analysis

Languages Studied: English

Keywords: multi-class sentiment analysis; in-context learning; multi-kernel Gaussian process

Submission Number: 7518