Malicious accounts detection from online social networks: a systematic review of literature

Abstract

The bourgeoning of Online Social Networks has triggered an increase in undesirable acts caused by some disruptive entities, e.g. fake accounts, bots, and cyber-extremists. Thence, detection systems for unveiling malicious accounts and mitigating their harmful behavior were taken by a storm. This paper presents a systematic review of the literature on malicious account detection and comprehensive analysis from a social network perspective. We critically explore the detection approaches to identify the unsolved problems in the domain. We scrutinized 147 articles to come out with the following findings: the targeted malicious accounts category, the list of features selected for the detection task, the social platform which offered features information, the application area that requires detection of malicious accounts, a comparison between detection methods, a comparison between available datasets, and the performance metrics used for validation. We also discuss the forthcoming challenges in terms of detection methods, annotation techniques, and validation protocols.

Keywords:

• Online social networks
• malicious accounts
• unwanted behavior
• machine learning
• systematic review of literature

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 http://www.fakenewschallenge.org

2 https://botometer.iuni.iu.edu/bot-repository/datasets.html

3 http://mib.projects.iit.cnr.it/dataset.html

4 https://developer.twitter.com/en/docs/tweets/data-dictionary/overview/entities-object

5 http://help.sentiment140.com/api

6 https://textblob.readthedocs.io/en/dev

7 https://github.com/nchavoshi/Debot_api

8 https://botometer.iuni.iu.edu

9 https://networkx.github.io

10 https://developer.twitter.com

11 https://developer.twitter.com/en/docs/tweets/timelines/overview

12 https://projects.honeynet.org/capture-hpc

13 https://developers.google.com/safe-browsing

14 https://giraph.apache.org

15 http://mahout.apache.org

16 https://spark.apache.org

17 http://english.hani.co.kr/arti/english_edition/e_international/926084.html

Additional information

Funding

The authors are supported by the ASTRA funding program Grant 2014-2020.4.01.16-032.

Notes on contributors

Imen Ben Sassi

Imen Ben Sassi is a post-doctoral researcher at Tallinn University of Technology, Department of Software Science since October 2019. She obtained her Ph.D. from the Faculty of Science of Tunis in December 2018. Her research interests focus on context-aware information retrieval, recommender systems, text analysis, machine learning techniques, and social network analysis.

Sadok Ben Yahia

Sadok Ben Yahia is a Professor at the Technology University of Tallinn (TalTech) since January 2019. He obtained his Habilitation to Lead research in Computer Sciences from the University of Montpellier in April 2009. His research interests mainly focus on combinatorial aspects in Big Data and their applications to different fields, e.g. Data mining, combinatorial analytics (e.g. maximum clique problem, minimal transversals), urban mobility in smart cities (e.g. information aggregation & dissemination, traffic congestion prediction). For the supervision activities, He supervised 33 PhD Computer Science Students and over 60 master students. A selected list of his publications is shown at a glance through his DBLP web site: http://dblp.uni-trier.de/pers/hd/y/Yahia:Sadok_Ben. In addition, the impact of his publications within the community is shown through the google scholar: https://scholar.google.com/citations?user=uJwhmiUAAAAJ&hl=fr. He is currently a member of the steering committee of the International Conference on Concept Lattices and their Applications (CLA) as well as the International French Spoken Conference on Knowledge Extractions and Management. Contact him at [email protected].