面向不平衡短文本情感多分类的三阶语义图数据增广方法  

A Short Text Augmentation Approach Based on Three-Order Semantic Graphs for Imbalanced Sentiment Multiclassification

作　　者：颜学明 黄翰[2,3,4] 金耀初 钟国 郝志峰 YAN Xueming;HUANG Han;JIN Yao-Chu;ZHONG Guo;HAO Zhi-Feng(School of Information Science and Technology,Guangdong University of Foreign Studies,Guangzhou 510006;School of Software Engineering,South China University of Technology,Guangzhou 510006;Key Laboratory of Big Data and Intelligent Robot,MOE of China,Guangzhou 510006;Guangdong Engineering Center for Large Model and Generative Artificial Intelligence Technology,Guangzhou 510006;School of Engineering,Westlake University,Hangzhou 310030;College of Mathematics and Computer Science,Shantou University,Shantou,Guangdong 515063)

机构地区：[1]广东外语外贸大学信息科学与技术学院,广州510006 [2]华南理工大学软件学院,广州510006 [3]大数据与智能机器人教育部重点实验室,广州510006 [4]广东省大模型与生成式人工智能技术工程中心,广州510006 [5]西湖大学工学院,杭州310030 [6]汕头大学数学与计算机学院,广东汕头515063

出　　处：《计算机学报》2024年第12期2742-2759,共18页Chinese Journal of Computers

基　　金：国家自然科学基金重点项目(62136003);国家自然科学基金项目(62276103,62476163);国家自然科学基金合作创新研究团队项目(W2441019);广东省基础与应用基础研究基金(2023B1515120020);广东省普通高校创新团队项目(2023KCXTD002)资助.

摘　　要：文本增广技术可以有效提升不平衡情感分类任务的性能.若文本增广过程中生成的少数类短文本数据未能体现完整的情感语义特征,则可能会导致不同类别之间的情感重叠问题出现.为了充分学习和理解少数类别的情感特征,本文提出一种面向不平衡文本情感多分类的三阶语义图数据增广方法,首先采用三阶语义图在多个词之间建立复杂的关系语义模型,用于表示多种可能的短文本局部情感语义和词节点依赖关系,然后提出了基于三阶语义图数据增广方法以平衡多分类文本的情感类别分布,从而有效实现不平衡短文本的情感分类.与传统的文本增广方法相比,在印尼语不平衡数据集上,本文提出的方法在少数类评价指标F1-measure和F2-measure上分别提升了5.75%和9.65%,在平衡情感识别能力指标G-means值上提升了2.91%;在马来语不平衡数据集上,本文提出的方法在少数类评价指标F1-measure和F3-measure上也分别提升了2.45%和4.81%,在平衡情感识别能力指标G-means值上提升了1.24%.此外,与传统的机器学习方法、深度网络模型等情感分类模型以及传统的短文本增广过采样模型相比,本文提出的方法在公开的印尼语、马来语、英语以及中文四个不平衡短文本数据集上都获得了最高的准确率Accuracy值.以上实验结果表明,融合不同模体的三阶语义图结构信息不仅可以有效表达文本中的局部情感语义以及词节点之间的依赖关系,还可以有效降低短文本数据增广过采样过程中引入新噪声的风险,并提升不平衡短文本的多分类性能.Text augmentation techniques have been widely recognized for their ability to significantly enhance the performance of sentiment classification tasks,particularly when dealing with imbalanced datasets.However,when generating short text data for the minority class during text augmentation,it can result in overlapping emotions across different categories if the generated data fails to capture the complete semantic features of sentiment.To better understand and represent the emotional features of minority classes,this study introduces a third-order semantic graph data augmentation method specifically designed for imbalanced text sentiment multiclassification.The proposed method is based on the construction of a third-order semantic graph that models complex relationships between multiple words within short texts.The proposed method allows for the representation of a wide range of local sentiment semantics and is able to capture the dependencies between word nodes,offering a more nuanced understanding of emotional context in minority classes.By leveraging this intricate relational model,the thirdorder semantic graph enables a more comprehensive representation of sentiment,ensuring that the emotional characteristics of minority classes are more accurately reflected in the generated data.Once the third-order semantic graph is constructed,a data augmentation method based on this graph is applied to balance the distribution of sentiment categories in multi-class text datasets.This approach is designated to address the shortcomings of traditional text augmentation methods that often introduce noise and fail to adequately represent minority class sentiments by ensuring that the generated text data can capture the essential emotional features of the minority class,thus leading to improved classification performance across imbalanced datasets.Compared with traditional text augmentation methods,the proposed method in this paper can improve the minority evaluation indicators F1-measure and F2-measure by 5.75% and 9.65%,respect

关 键 词：三阶语义图 文本增广 平衡策略 短文本情感分类 模体 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]