Based on Data Balancing and Model Improvement for Multi-Label Sentiment Classification Performance Enhancement

TL;DR

This paper introduces a balanced multi-label sentiment dataset and an improved classification model that leverages data balancing, advanced neural architectures, and mixed precision training to enhance sentiment detection accuracy.

Contribution

The study presents a novel data balancing strategy and a multi-component neural model that significantly improves multi-label sentiment classification performance.

Findings

Balanced dataset across 28 emotions improves model fairness.

Enhanced model achieves higher accuracy, precision, recall, F1-score, and AUC.

Data balancing and model improvements outperform previous methods.

Abstract

Multi-label sentiment classification plays a vital role in natural language processing by detecting multiple emotions within a single text. However, existing datasets like GoEmotions often suffer from severe class imbalance, which hampers model performance, especially for underrepresented emotions. To address this, we constructed a balanced multi-label sentiment dataset by integrating the original GoEmotions data, emotion-labeled samples from Sentiment140 using a RoBERTa-base-GoEmotions model, and manually annotated texts generated by GPT-4 mini. Our data balancing strategy ensured an even distribution across 28 emotion categories. Based on this dataset, we developed an enhanced multi-label classification model that combines pre-trained FastText embeddings, convolutional layers for local feature extraction, bidirectional LSTM for contextual learning, and an attention mechanism to highlight sentiment-relevant words. A sigmoid-activated output layer enables multi-label prediction, and mixed precision training improves computational efficiency. Experimental results demonstrate significant improvements in accuracy, precision, recall, F1-score, and AUC compared to models trained on imbalanced data, highlighting the effectiveness of our approach.