通过平衡数据与模型优化，提升多标签情感分类效果
Based on Data Balancing and Model Improvement for Multi-Label Sentiment Classification Performance Enhancement
- 构建包含28类情绪的均衡数据集，融合真实与生成样本
- 新模型在准确率、F1等指标上显著优于原始不平衡数据训练结果
- 适合关注情感分析中少数类别表现的研究者与应用开发者
多标签情感分类在自然语言处理中至关重要，用于识别单段文本中的多种情绪。然而，现有数据集如GoEmotions常存在严重类别不平衡问题，导致模型对少数情绪识别能力差。为此，我们基于原始GoEmotions数据，结合使用RoBERTa-base-GoEmotions模型从Sentiment140获取的情绪标注样本，以及GPT-4 mini生成的手动标注文本，构建了一个28类情绪均衡的多标签情感数据集。在此基础上，提出一种增强型多标签分类模型，融合预训练FastText嵌入、卷积层提取局部特征、双向LSTM捕捉上下文信息，并引入注意力机制突出情感关键词。输出层采用Sigmoid激活，支持多标签预测，混合精度训练提升计算效率。实验表明，该方法在准确率、精确率、召回率、F1分数和AUC上均显著优于在不平衡数据上训练的模型，验证了其有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。