Social Robot Detection Method with Improved Graph Neural Networks

作     者：Zhenhua Yu Liangxue Bai Ou Ye Xuya Cong 

作者机构：Institute of Systems Security and ControlCollege of Computer Science and TechnologyXi’an University of Science and TechnologyXi’an710054China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第78卷第2期

页      面：1773-1795页

核心收录：

学科分类：07[理学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 070101[理学-基础数学] 

基　　金：This work was supported in part by the National Natural Science Foundation of China under Grants 62273272,62303375 and 61873277 in part by the Key Research and Development Program of Shaanxi Province under Grant 2023-YBGY-243 in part by the Natural Science Foundation of Shaanxi Province under Grants 2022JQ-606 and 2020-JQ758 in part by the Research Plan of Department of Education of Shaanxi Province under Grant 21JK0752 in part by the Youth Innovation Team of Shaanxi Universities 

主　　题：Social robot detection social relationship subgraph graph attention network feature linear modulation behavioral gene sequences 

摘      要：Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social *** social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social *** paper proposes a social robot detection method with the use of an improved neural ***,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships ***,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the ***,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph ***,social robots can be more accurately identified by combining user behavioral and relationship *** carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,*** with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two *** results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.