MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection
Social media bots pose potential threats to the online environment, and the continuously evolving anti-detection technologies require bot detection methods to be more reliable and general. Current detection methods encounter challenges, including limited generalization ability, susceptibility to eva...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/10/2298 |
_version_ | 1797600299849875456 |
---|---|
author | Fanrui Zeng Yingjie Sun Yizhou Li |
author_facet | Fanrui Zeng Yingjie Sun Yizhou Li |
author_sort | Fanrui Zeng |
collection | DOAJ |
description | Social media bots pose potential threats to the online environment, and the continuously evolving anti-detection technologies require bot detection methods to be more reliable and general. Current detection methods encounter challenges, including limited generalization ability, susceptibility to evasion in traditional feature engineering, and insufficient exploration of user relationships. To tackle these challenges, this paper proposes MRLBot, a social media bot detection framework based on unsupervised representation learning. We design a behavior representation learning model that utilizes Transformer and a CNN encoder–decoder to simultaneously extract global and local features from behavioral information. Furthermore, a network representation learning model is proposed that introduces intra- and outer-community-oriented random walks to learn structural features and community connections from the relationship graph. Finally, the behavioral representation and relationship representation learning models are combined to generate fused representations for bot detection. The experimental results of four publicly available social network datasets demonstrate that the proposed method has certain advantages over state-of-the-art detection methods in this field. |
first_indexed | 2024-03-11T03:46:33Z |
format | Article |
id | doaj.art-41a9dc6f4f524669897bb31bf8a1be87 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T03:46:33Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-41a9dc6f4f524669897bb31bf8a1be872023-11-18T01:10:27ZengMDPI AGElectronics2079-92922023-05-011210229810.3390/electronics12102298MRLBot: Multi-Dimensional Representation Learning for Social Media Bot DetectionFanrui Zeng0Yingjie Sun1Yizhou Li2School of Cyber Science and Engineering, Sichuan University, Chengdu 610065, ChinaSchool of Cyber Science and Engineering, Sichuan University, Chengdu 610065, ChinaSchool of Cyber Science and Engineering, Sichuan University, Chengdu 610065, ChinaSocial media bots pose potential threats to the online environment, and the continuously evolving anti-detection technologies require bot detection methods to be more reliable and general. Current detection methods encounter challenges, including limited generalization ability, susceptibility to evasion in traditional feature engineering, and insufficient exploration of user relationships. To tackle these challenges, this paper proposes MRLBot, a social media bot detection framework based on unsupervised representation learning. We design a behavior representation learning model that utilizes Transformer and a CNN encoder–decoder to simultaneously extract global and local features from behavioral information. Furthermore, a network representation learning model is proposed that introduces intra- and outer-community-oriented random walks to learn structural features and community connections from the relationship graph. Finally, the behavioral representation and relationship representation learning models are combined to generate fused representations for bot detection. The experimental results of four publicly available social network datasets demonstrate that the proposed method has certain advantages over state-of-the-art detection methods in this field.https://www.mdpi.com/2079-9292/12/10/2298social media botsrepresentation learningencoder–decodergraph embedding |
spellingShingle | Fanrui Zeng Yingjie Sun Yizhou Li MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection Electronics social media bots representation learning encoder–decoder graph embedding |
title | MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection |
title_full | MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection |
title_fullStr | MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection |
title_full_unstemmed | MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection |
title_short | MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection |
title_sort | mrlbot multi dimensional representation learning for social media bot detection |
topic | social media bots representation learning encoder–decoder graph embedding |
url | https://www.mdpi.com/2079-9292/12/10/2298 |
work_keys_str_mv | AT fanruizeng mrlbotmultidimensionalrepresentationlearningforsocialmediabotdetection AT yingjiesun mrlbotmultidimensionalrepresentationlearningforsocialmediabotdetection AT yizhouli mrlbotmultidimensionalrepresentationlearningforsocialmediabotdetection |