Markov-Driven Graph Convolutional Networks for Social Spammer Detection

被引:14
|
作者
Deng, Leyan [1 ]
Wu, Chenwang [1 ]
Lian, Defu [2 ]
Wu, Yongji [3 ]
Chen, Enhong [2 ]
机构
[1] Univ Sci & Technol China, Sch Data Sci, Hefei 230000, Anhui, Peoples R China
[2] Univ Sci & Technol China, Sch Comp Sci & Technol, Anhui Prov Key Lab Big Data Anal & Applicat, Hefei 230000, Anhui, Peoples R China
[3] Duke Univ, Dept Comp Sci, Durham, NC 27706 USA
基金
中国国家自然科学基金;
关键词
Social networking (online); Feature extraction; Probability distribution; Blogs; Adaptation models; Markov random fields; Robustness; Spammer detection; graph convolutional networks;
D O I
10.1109/TKDE.2022.3150669
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the growing popularity of social media, malicious users (spammers) unfairly overpower legitimate users with unwanted or fake content to achieve their illegal purposes, which encourages research on spammer detection. The existing spammer detection methods can be characterized into feature-based detection and propagation-based detection. However, feature-based methods (e.g., GCN) cannot capture the user's following relations, while propagation-based methods cannot utilize the rich text features. To this end, we consider combining these two methods and propose an Adaptive Reward Markov Random Field (ARMRF) layer. ARMRF layer models three intuitions on user label relations and assign them different learnable rewards. Besides, we learn the reward weights by stacking the ARMRF layer on top of GCN for end-to-end training, and we call the stacked model ARMGCN. To further improve the expressive power of ARMGCN, we propose the Markov-Driven Graph Convolutional Network (MDGCN), which integrates conditional random fields (CRF) and ARMGCN. CRF establishes the label joint probability distribution conditioned features for learning user dependencies, and the distribution can be optimized by a variational EM algorithm. We extensively evaluate the proposed method on two real-world Twitter datasets, and the experimental results demonstrate that MDGCN outperforms the state-of-the-art baselines. In addition, the ARMRF layer is model-independent, so it can be integrated with existing advanced detection methods to improve detection performance further.
引用
收藏
页码:12310 / 12322
页数:13
相关论文
共 50 条
  • [41] CLASSIFIER ENSEMBLES USING STRUCTURAL FEATURES FOR SPAMMER DETECTION IN ONLINE SOCIAL NETWORKS
    Abulaish, Muhammad
    Bhat, Sajid Y.
    FOUNDATIONS OF COMPUTING AND DECISION SCIENCES, 2015, 40 (02) : 89 - 105
  • [42] UCoDe: unified community detection with graph convolutional networks
    Moradan, Atefeh
    Draganov, Andrew
    Mottin, Davide
    Assent, Ira
    MACHINE LEARNING, 2023, 112 (12) : 5057 - 5080
  • [43] Graph-based review spammer group detection
    Zhuo Wang
    Songmin Gu
    Xiangnan Zhao
    Xiaowei Xu
    Knowledge and Information Systems, 2018, 55 : 571 - 597
  • [44] UCoDe: unified community detection with graph convolutional networks
    Atefeh Moradan
    Andrew Draganov
    Davide Mottin
    Ira Assent
    Machine Learning, 2023, 112 : 5057 - 5080
  • [45] Multiple Rumor Source Detection with Graph Convolutional Networks
    Dong, Ming
    Zheng, Bolong
    Nguyen Quoc Viet Hung
    Su, Han
    Li, Guohui
    PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, : 569 - 578
  • [46] Temporal Graph Convolutional Networks for Automatic Seizure Detection
    Covert, Ian C.
    Krishnan, Balu
    Najm, Imad
    Zhan, Jiening
    Shore, Matthew
    Hixson, John
    Po, Ming Jack
    MACHINE LEARNING FOR HEALTHCARE CONFERENCE, VOL 106, 2019, 106
  • [47] Graph Convolutional Adversarial Networks for Spatiotemporal Anomaly Detection
    Deng, Leyan
    Lian, Defu
    Huang, Zhenya
    Chen, Enhong
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (06) : 2416 - 2428
  • [48] Unified Line and Paragraph Detection by Graph Convolutional Networks
    Liu, Shuang
    Wang, Renshen
    Raptis, Michalis
    Fujii, Yasuhisa
    DOCUMENT ANALYSIS SYSTEMS, DAS 2022, 2022, 13237 : 33 - 47
  • [49] Malware detection with dynamic evolving graph convolutional networks
    Zhang, Zikai
    Li, Yidong
    Wang, Wei
    Song, Haifeng
    Dong, Hairong
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2022, 37 (10) : 7261 - 7280
  • [50] Guardian: Evaluating Trust in Online Social Networks with Graph Convolutional Networks
    Lin, Wanyu
    Gao, Zhaolin
    Li, Baochun
    IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS, 2020, : 914 - 923