Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction

TL;DR

This paper introduces CISEA-MRFE, a novel deep learning framework that enhances sentiment analysis by integrating contextual instructions, semantic augmentation, and multi-scale feature extraction, leading to improved accuracy across diverse datasets.

Contribution

The paper presents a new PLM-based framework combining CI, SEA, and MRFE to address limitations in nuanced, domain-shifted, and imbalanced sentiment analysis tasks.

Findings

Outperforms strong baselines on four benchmark datasets.

Achieves up to 30.3% accuracy improvement on Twitter.

Demonstrates robust generalization across domains.

Abstract

Sentiment analysis using deep learning and pre-trained language models (PLMs) has gained significant traction due to their ability to capture rich contextual representations. However, existing approaches often underperform in scenarios involving nuanced emotional cues, domain shifts, and imbalanced sentiment distributions. We argue that these limitations stem from inadequate semantic grounding, poor generalization to diverse linguistic patterns, and biases toward dominant sentiment classes. To overcome these challenges, we propose CISEA-MRFE, a novel PLM-based framework integrating Contextual Instruction (CI), Semantic Enhancement Augmentation (SEA), and Multi-Refined Feature Extraction (MRFE). CI injects domain-aware directives to guide sentiment disambiguation; SEA improves robustness through sentiment-consistent paraphrastic augmentation; and MRFE combines a Scale-Adaptive Depthwise Encoder (SADE) for multi-scale feature specialization with an Emotion Evaluator Context Encoder (EECE) for affect-aware sequence modeling. Experimental results on four benchmark datasets demonstrate that CISEA-MRFE consistently outperforms strong baselines, achieving relative improvements in accuracy of up to 4.6% on IMDb, 6.5% on Yelp, 30.3% on Twitter, and 4.1% on Amazon. These results validate the effectiveness and generalization ability of our approach for sentiment classification across varied domains.