BotCL: a social bot detection model based on graph contrastive learning

IF 2.5 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Knowledge and Information Systems Pub Date : 2024-04-26 DOI:10.1007/s10115-024-02116-4
Yan Li, Zhenyu Li, Daofu Gong, Qian Hu, Haoyu Lu
{"title":"BotCL: a social bot detection model based on graph contrastive learning","authors":"Yan Li, Zhenyu Li, Daofu Gong, Qian Hu, Haoyu Lu","doi":"10.1007/s10115-024-02116-4","DOIUrl":null,"url":null,"abstract":"<p>The proliferation of social bots on social networks presents significant challenges to network security due to their malicious activities. While graph neural network models have shown promise in detecting social bots, acquiring a large number of high-quality labeled accounts remains challenging, impacting bot detection performance. To address this issue, we introduce BotCL, a social bot detection model that employs contrastive learning through data augmentation. Initially, we build a directed graph based on following/follower relationships, utilizing semantic, attribute, and structural features of accounts as initial node features. We then simulate account behaviors within the social network and apply two data augmentation techniques to generate multiple views of the directed graph. Subsequently, we encode the generated views using relational graph convolutional networks, achieving maximum homogeneity in node representations by minimizing the contrastive loss. Finally, node labels are predicted using Softmax. The proposed method augments data based on its distribution, showcasing robustness to noise. Extensive experimental results on Cresci-2015, Twibot-20, and Twibot-22 datasets demonstrate that our approach surpasses the state-of-the-art methods in terms of performance.</p>","PeriodicalId":54749,"journal":{"name":"Knowledge and Information Systems","volume":"15 1","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge and Information Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10115-024-02116-4","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

The proliferation of social bots on social networks presents significant challenges to network security due to their malicious activities. While graph neural network models have shown promise in detecting social bots, acquiring a large number of high-quality labeled accounts remains challenging, impacting bot detection performance. To address this issue, we introduce BotCL, a social bot detection model that employs contrastive learning through data augmentation. Initially, we build a directed graph based on following/follower relationships, utilizing semantic, attribute, and structural features of accounts as initial node features. We then simulate account behaviors within the social network and apply two data augmentation techniques to generate multiple views of the directed graph. Subsequently, we encode the generated views using relational graph convolutional networks, achieving maximum homogeneity in node representations by minimizing the contrastive loss. Finally, node labels are predicted using Softmax. The proposed method augments data based on its distribution, showcasing robustness to noise. Extensive experimental results on Cresci-2015, Twibot-20, and Twibot-22 datasets demonstrate that our approach surpasses the state-of-the-art methods in terms of performance.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
BotCL:基于图对比学习的社交机器人检测模型
由于社交机器人的恶意活动,它们在社交网络上的扩散给网络安全带来了巨大挑战。虽然图神经网络模型在检测社交僵尸方面已显示出良好的前景,但获取大量高质量的标签账户仍具有挑战性,从而影响了僵尸检测性能。为了解决这个问题,我们引入了 BotCL,这是一种通过数据增强进行对比学习的社交僵尸检测模型。起初,我们基于关注/粉丝关系构建有向图,利用账户的语义、属性和结构特征作为初始节点特征。然后,我们模拟账户在社交网络中的行为,并应用两种数据增强技术生成有向图的多个视图。随后,我们使用关系图卷积网络对生成的视图进行编码,通过最小化对比损失实现节点表示的最大同质性。最后,使用 Softmax 预测节点标签。所提出的方法根据数据的分布对数据进行了增强,展示了对噪声的鲁棒性。在 Cresci-2015、Twibot-20 和 Twibot-22 数据集上的大量实验结果表明,我们的方法在性能上超越了最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Knowledge and Information Systems
Knowledge and Information Systems 工程技术-计算机:人工智能
CiteScore
5.70
自引率
7.40%
发文量
152
审稿时长
7.2 months
期刊介绍: Knowledge and Information Systems (KAIS) provides an international forum for researchers and professionals to share their knowledge and report new advances on all topics related to knowledge systems and advanced information systems. This monthly peer-reviewed archival journal publishes state-of-the-art research reports on emerging topics in KAIS, reviews of important techniques in related areas, and application papers of interest to a general readership.
期刊最新文献
Dynamic evolution of causal relationships among cryptocurrencies: an analysis via Bayesian networks Deep multi-semantic fuzzy K-means with adaptive weight adjustment Class incremental named entity recognition without forgetting Spectral clustering with scale fairness constraints Supervised kernel-based multi-modal Bhattacharya distance learning for imbalanced data classification
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1