基于文本语义和社交行为信息融合的讽刺检测方法  

Sarcasm detection method based on fusion of text semantics and social behavior information

作　　者：付朝阳 陈致凯 潘理[1,2,3] FU Zhaoyang;CHEN Zhikai;PAN Li(Institute of Cyber Science and Technology,Shanghai Jiao Tong University,Shanghai 200240,China;Shanghai Municipal Key Lab of Integrated Management Technology for Information Security,Shanghai 200240,China;Zhang jiang Institute for Advanced Study,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]上海交通大学网络安全技术研究院,上海200240 [2]信息安全综合管理技术研究上海市重点实验室,上海200240 [3]上海交通大学张江高等研究院,上海200240

出　　处：《网络与信息安全学报》2023年第4期134-143,共10页Chinese Journal of Network and Information Security

基　　金：国家自然科学基金(62172278)。

摘　　要：讽刺是一种复杂的隐式情感,讽刺检测是文本情感分析领域的重要研究问题,对于社交网络舆情分析有极强的现实意义。讽刺文本的表层语义和用户的真实情感往往相反,基于表层语义的文本情感检测通常会得到错误的分类结果。日常交流中的讽刺往往借助语调、神态等非文本信息进行表达,因此单纯基于文本语义的讽刺检测方法无法利用非文本信息,极大地制约了检测效果。为了充分利用文本语义与用户社交行为信息,提升讽刺检测效果,提出了一种基于文本语义和社交行为信息融合的讽刺检测方法。该方法构造了包含用户、文本、情感词的异质信息网络,并设计了一种用于异质信息图表征向量计算的图神经网络模型。该模型使用双重注意力机制提取社交行为信息,通过情感子图挖掘文本深层语义,最终得到融合文本语义和社交行为信息的融合特征向量。融合特征向量可以用于训练分类器,进而完成社交网络文本讽刺检测。在推特真实数据集上的充分实验表明,所提方法的分类效果优于现有的讽刺文本检测方法。Sarcasm is a complex implicit emotion that poses a significant challenge in sentiment analysis,particularly in social network sentiment analysis.Effective sarcasm detection holds immense practical significance in the analysis of network public opinion.The contradictory nature of sarcastic texts,which exhibit implicit semantics opposite to the real emotions of users,often leads to misclassification by traditional sentiment analysis methods.Moreover,sarcasm in daily communication is often conveyed through non-textual cues such as intonation and demeanor.Consequently,sarcasm detection methods solely relying on text semantics fail to incorporate non-textual information,thereby limiting their effectiveness.To leverage the power of text semantics and social behavior information,a sarcasm text detection method based on heterogeneous graph information fusion was proposed.The approach involved the construction of a heterogeneous information network encompassing users,texts,and emotional words.A graph neural network model was then designed to handle the representations of the heterogeneous graph.The model employed a dual-channel attention mechanism to extract social behavior information,captured the deep semantics of text through emotional subgraphs,and ultimately combined text semantics and social behavior information.Extensive experiments conducted on the Twitter dataset demonstrate the superiority of the proposed method over existing approaches for sarcasm text detection and classification.

关 键 词：讽刺检测 图神经网络 异质信息融合 隐式情感分析 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]