Boosting Social Spam Detection via Attention Mechanisms on Twitter

被引:3
|
作者
Shen, Hua [1 ,2 ,3 ]
Liu, Xinyue [2 ]
Zhang, Xianchao [2 ]
机构
[1] Dalian Univ Technol, Fac Elect Informat & Elect Engn, Dalian 116024, Peoples R China
[2] Dalian Univ Technol, Sch Software, Dalian 116620, Peoples R China
[3] Anshan Normal Univ, Coll Math & Informat Sci, Anshan 114007, Peoples R China
基金
中国国家自然科学基金;
关键词
attention mechanism; graph attention network; BERTweet pretrained model; social spam detection; GRAPH NEURAL-NETWORK;
D O I
10.3390/electronics11071129
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Twitter is one of the largest social networking platforms, which allows users to make friends, read the latest news, share personal ideas, and discuss social issues. The huge popularity of Twitter mean it attracts a lot of online spammers. Traditional spam detection approaches have shown the effectiveness for identifying Twitter spammers by extracting handcrafted features and training machine learning models. However, such models need knowledge from domain experts. Moreover, the behaviors of spammers can change according to the defense strategies of Twitter. These result in the ineffectiveness of the traditional feature-based approaches. Although deep-learning-based approaches have been proposed for detecting Twitter spammers, they all treat each tweet equally, and ignore the differences among them. To solve these issues, in this paper, we propose a new attention-based deep learning model to detect social spammers in Twitter. In particular, we first introduce the state-of-the-art pretraining model BERTweet for learning the representation of each tweet, and then use the proposed novel attention-based mechanism to learn the user representations by distinguishing the differences among tweets posted by each user. Moreover, we take social interactions into consideration and propose that a graph attention network is used to update the learned user representations, to further improve the accuracy of identifying spammers. Experiments on a publicly available, real-world Twitter dataset show the effectiveness of the proposed model, which is able to significantly enhance the performance.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] A Social Spam Detection Framework via Semi-supervised Learning
    Zhang, Xianchao
    Bai, Haijun
    Liang, Wenxin
    [J]. TRENDS AND APPLICATIONS IN KNOWLEDGE DISCOVERY AND DATA MINING (PAKDD 2016), 2016, 9794 : 214 - 226
  • [32] An Attention-Based Graph Neural Network for Spam Bot Detection in Social Networks
    Zhao, Chensu
    Xin, Yang
    Li, Xuefeng
    Zhu, Hongliang
    Yang, Yixian
    Chen, Yuling
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (22): : 1 - 15
  • [33] Topic-aware neural attention network for malicious social media spam detection
    Nasser, Maged
    Saeed, Faisal
    Da'u, Aminu
    Alblwi, Abdulaziz
    Al-Sarem, Mohammed
    [J]. Alexandria Engineering Journal, 2025, 111 : 540 - 554
  • [34] Statistical Twitter Spam Detection Demystified: Performance, Stability and Scalability
    Lin, Guanjun
    Sun, Nan
    Nepal, Surya
    Zhang, Jun
    Xiang, Yang
    Hassan, Houcine
    [J]. IEEE ACCESS, 2017, 5 : 11142 - 11154
  • [35] Statistical Detection of Online Drifting Twitter Spam [Invited Paper]
    Liu, Shigang
    Zhang, Jun
    Xiang, Yang
    [J]. ASIA CCS'16: PROCEEDINGS OF THE 11TH ACM ASIA CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, : 1 - 10
  • [36] Spamming the Mainstream: A Survey on Trending Twitter Spam Detection Techniques
    Lalitha, L. A.
    Hulipalled, Vishwanath R.
    Venugopal, K. R.
    [J]. PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES FOR SMART NATION (SMARTTECHCON), 2017, : 444 - 448
  • [37] Twitter spam detection: Survey of new approaches and comparative study
    Wu, Tingmin
    Wen, Sheng
    Xiang, Yang
    Zhou, Wanlei
    [J]. COMPUTERS & SECURITY, 2018, 76 : 265 - 284
  • [38] Twitter spam account detection based on clustering and classification methods
    Kayode Sakariyah Adewole
    Tao Han
    Wanqing Wu
    Houbing Song
    Arun Kumar Sangaiah
    [J]. The Journal of Supercomputing, 2020, 76 : 4802 - 4837
  • [39] A comparative study of the class imbalance problem in Twitter spam detection
    Li, Chaoliang
    Liu, Shigang
    [J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2018, 30 (05):
  • [40] Twitter spam account detection based on clustering and classification methods
    Adewole, Kayode Sakariyah
    Hang, Tao
    Wu, Wanqing
    Songs, Houbing
    Sangaiah, Arun Kumar
    [J]. JOURNAL OF SUPERCOMPUTING, 2020, 76 (07): : 4802 - 4837