多粒度特征融合的分层式机器学习情感分析OA
Hierarchical Machine Learning Sentiment Analysis of Multi-Granularity Feature Fusion
针对现有情感分析方法在多类别文本分类任务中对语义特征利用不足的问题,提出多粒度特征融合的分层式机器学习情感分析模型.首先,利用极限梯度提升(XGBoost)算法与支持向量机(SVM)并行进行基础分类,分别生成10个类别概率分布;然后,以逻辑回归作为元分类器,对双通道输出结果实施特征级融合;最后,对10个类别共计62 774条评论的公开数据集进行验证.实验结果表明:HML-MGFF模型准确率较传统单分类器模型平均提升15.6％,较其他4种复合模型平均提升4.6％.
To address the insufficient utilization of semantic features in esisting sentiment analysis methods for multi-category text classification tasks,a hierarchical sentiment analysis model based on multi-granularity feature fusion is proposed.First,the extreme gradient boosting(XGBoost)algorithm and support vector ma-chine(SVM)are employed in parallel for basic classification,each generating probability distributions across 10 categories.Then,logistic regression is adopted as a meta-classifier to perform feature-level fusion of the du-al channel output results.Finally,the model is validated on a public dataset containing 62 774 comments across 10 categories.Experimental results show that the HML-MGFF model achieves an average accuracy improve-ment of 15.6％over traditional single-classifier models,and 4.6％over four other composite models.
赵金鑫;郭荣新;施一帆
华侨大学工学院,福建泉州 362021华侨大学工学院,福建泉州 362021华侨大学工学院,福建泉州 362021
信息技术与安全科学
多粒度特征融合分层式机器学习极限梯度提升支持向量机逻辑回归
multi-granularity feature fusionhierarchical machine learninglimit gradient liftingsupport vec-tor machinelogistic regression
《华侨大学学报（自然科学版）》 2026 (2)
164-174,11
国家自然科学基金青年基金资助项目(62306122)福建省科技项目引导性项目(2023H0012)
评论