Detection of Social Network Spam Based on Improved Extreme Learning Machine

被引：18

作者：

Zhang, Zhijie ^{[1
]}

Hou, Rui ^{[1
]}

Yang, Jin ^{[2
]}

机构：

[1] Lingnan Normal Univ, Sch Informat Engn, Zhanjiang 524048, Peoples R China

[2] Guangdong Pharmaceut Univ, Sch Med Informat & Engn, Guangzhou 510006, Peoples R China

来源：

IEEE ACCESS | 2020年 / 8卷

关键词：

Twitter; Feature extraction; Classification algorithms; Machine learning algorithms; Support vector machines; Radio frequency; Social network; spam detection; spam features; machine learning; I2FELM;

D O I：

10.1109/ACCESS.2020.3002940

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

With the rapid advancement of the online social network, social media like Twitter has been increasingly critical to real life and become the prime objective of spammers. Twitter spam detection refers to a complex task for the involvement of a range of characteristics, and spam and non-spam have caused unbalanced data distribution in Twitter. To solve the mentioned problems, Twitter spam characteristics are analyzed as the user attribute, content, activity and relationship in this study, and a novel spam detection algorithm is designed based on regularized extreme learning machine, called the Improved Incremental Fuzzy-kernel-regularized Extreme Learning Machine (I2FELM), which is used to detect the Twitter spam accurately. As revealed from the experience validation results, the proposed I2FELM can efficiently identify the balanced and unbalanced dataset. Moreover, with few characteristics taken, the I2FELM can more effectively detect spam, which proves the effectiveness of the algorithm.

引用

页码：112003 / 112014

页数：12

共 50 条

[21] Machine Learning for the Detection of Spam in Twitter Networks
Wang, Alex Hai
E-BUSINESS AND TELECOMMUNICATIONS, 2012, 222 : 319 - 333
[22] A Study of Machine Learning Classifiers for Spam Detection
Trivedi, Shrawan Kumar
2016 4TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL AND BUSINESS INTELLIGENCE (ISCBI), 2016, : 176 - 180
[23] Comparison of Machine Learning Algorithms for Spam Detection
Sadia, Azeema
Bashir, Fatima
Khan, Reema Qaiser
Bashir, Amna
Khalid, Ammarah
JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY, 2023, 14 (02) : 178 - 184
[24] Comparison of machine learning techniques for spam detection
Argha Ghosh
A. Senthilrajan
Multimedia Tools and Applications, 2023, 82 : 29227 - 29254
[25] Review Spam Detection using Machine Learning
Radovanovic, Drasko
Krstajic, Boza
2018 23RD INTERNATIONAL SCIENTIFIC-PROFESSIONAL CONFERENCE ON INFORMATION TECHNOLOGY (IT), 2018,
[26] Spam Detection Using Machine Learning in R
Kumari, K. R. Vidya
Kavitha, C. R.
INTERNATIONAL CONFERENCE ON COMPUTER NETWORKS AND COMMUNICATION TECHNOLOGIES (ICCNCT 2018), 2019, 15 : 55 - 64
[27] Improved machine learning technique for feature reduction and its application in spam email detection
Ewees, Ahmed A.
Gaheen, Marwa A.
Alshahrani, Mohammed M.
Anter, Ahmed M.
Ismail, Fatma H.
JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2024, 62 (06) : 1749 - 1771
[28] A spam filter approach with the improved machine learning technology
Pang, Xiu-Li
Feng, Yu-Qiang
Jiang, Wei
ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 2, PROCEEDINGS, 2007, : 484 - +
[29] Anomaly detection in network traffic using extreme learning machine
Imamverdiyev, Yadigar
Sukhostat, Lyudmila
2016 IEEE 10TH INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES (AICT), 2016, : 418 - 421
[30] Advances in spam detection for email spam, web spam, social network spam, and review spam: ML-based and nature-inspired-based techniques
Akinyelu, Andronicus A.
JOURNAL OF COMPUTER SECURITY, 2021, 29 (05) : 473 - 529

← 1 2 3 4 5 →