Paper ID: 9053

Utilizing Supervised and Unsupervised Mining Techniques for Detecting Fake Facebook Profiles

Mohammed Basil Albayati*, Ahmad Mousa Altamimi

Department of Computer Science,

Applied Science Private University, Al Arab St. 21 Amman 11931, Jordan

*E-mail: mohammed.sabri@asu.edu.jo

 

Abstract

Facebook, a popular online social network site, has changed our modern life. Users can create a customized profile to share information about themselves with others that have agreed to be their friend. However, such gigantic technology tends to be misused for carrying out a number of malicious activities. Facebook faces a big problem of fake accounts where Scammers can violate users’ privacy by creating fake profiles to infiltrate personal social networks. In fact, many techniques are proposed to address this issue. Most of them are based on detecting the fake profiles/accounts considering the characteristics of the user’s profile. However, the limited publicly available profile data of Facebook makes it ineligible in applying the existing approaches in fake profile identification. Therefore, this research utilizes data mining techniques to detect fake profiles. A set of Supervised (ID3 decision tree, k-NN, and SVM) and Unsupervised (k-Means and k-Medoids) algorithms are applied on 12 behavioral and non-behavioral discriminative profiles attributes with a dataset of 982 profiles. Results showed that ID3 has the highest accuracy while k-Medoids registered the lowest accuracy in the detection process.

Keywords: Facebook; fake profiles; machine learning; supervised algorithms; unsupervised algorithms.

References

Smith, Andrew N and Fischer, Eileen and Yongjian, Chen, How does brand-related user-generated content differ across YouTube, Facebook, and Twitter?, Journal of interactive marketing, Vol. 26, No. 2, pp. 102-113, 2012.

Romero, Daniel, M., Galuba, W., Asur, S. & Bernardo, A., Influence and Passivity in Social Media, In Proceedings of the 20th International Conference Companion on World Wide Web, ACM, pp. 113-114,2011.

Obar, Jonathan, A. & Wildman, S.S., Social Media Definition and The Governance Challenge: An Introduction to The Special Issue, 2015.

Kaplan, Andreas, M. & Haenlein, M., Users of the World, Unite! The Challenges and Opportunities of Social Media, Business Horizons, 53(1), pp. 59-68, 2010.

Eugene, A., Castillo, C., Donato, D., Gionis, A. & Mishne, G., Finding High-Quality Content in Social Media, In Proceedings of the 2008 International Conference on Web Search and Data Mining, ACM, pp. 183-194, 2008

O'Keeffe., Schurgin, G. & Pearson, K.C., He Impact of Social Media on Children, Adolescents, and Families, Pediatrics. 127(4), pp. 800-804, 2011.

Qian, T., Gu, B. & Whinston, A.B., Content Contribution for Revenue Sharing and Reputation in Social Media: A Dynamic Structural Model, Journal of Management Information Systems, 29(2), pp. 41-76, 2012.

Kontaxis, Georgios, Polakis, I., Ioannidis, S. & Markatos, E.P., Detecting Social Network Profile Cloning, In Pervasive Computing and Communications Workshops (PERCOM Workshops), 2011 IEEE International Conference on, pp. 295-300. IEEE, 2011.

Wani, M.A, Jabin, S. & Ahmad, N., A Sneak into the Devil's Colony-Fake Profiles in Online Social Networks, arXiv preprint arXiv:1705.09929 ,2017.

RapidMiner. https://rapidminer.com/ (3rd August 2019).

Kumar, N. & Reddy, R.N., Automatic Detection of Fake Profiles in Online Social Networks." Ph.D. diss., National Institute of Technology Rourkela, 2012.

Gupta, A. & Kaushal, R., Towards Detecting Fake User Accounts in Facebook, In Asia Security and Privacy (ISEASP), 2017 ISEA, pp. 1-6. IEEE, 2017.

Ahmed, F. & Abulaish, M., A Generic Statistical Approach for Spam Detection in Online Social Networks, Computer Communications, 36(10), pp. 1120-1129, 2013.

Fire, M., Kagan, D., Elyashar, & Elovici, Y, Friend or Foe? Fake Profile Identification in Online Social Networks, Social Network Analysis and Mining, 4(1), pp.  194-210, 2014.

Nazir. A., Raza, S., Chuah, C.N., Schipper, B. & Davis, C.A., Ghostbusting Facebook: Detecting and Characterizing Phantom Profiles in Online Social Gaming Applications, In WOSN, 2010.

Xiaoyun, W., Lai, C.M., Hong, Y., Hsieh, C.J. & Wu, S.F., Multiple Accounts Detection on Facebook Using Semi-Supervised Learning on Graphs, arXiv preprint arXiv:1801.09838, 2018.

Bimal, V., Bashir, M.A., Crovella, M., Guha, S., Gummadi, K.P., Krishnamurthy, B. & Mislove, A., Towards Detecting Anomalous User Behavior in Online Social Networks, In USENIX Security Symposium, pp. 223-238, 2014.

Shalinda, A. & Dutta, K., Identifying Fake Profiles in LinkedIn, In PACIS, pp. 278. 2014.

Jiawei, H., Pei, J. & Kamber, M., Data Mining: Concepts and Techniques. Elsevier, 2011.

Karel, H., Matthias Templ. & Filzmoser, P., Imputation of Missing Values for Compositional Data Using Classical and Robust Methods, Computational Statistics & Data Analysis, 54(12), pp. 3095-3107, 2010.

Yousuf, B.S. & Abulaish, M., Community-Based Features for Identifying Spammers in Online Social Networks, In Advances in Social Networks Analysis and Mining (ASONAM), 2013 IEEE/ACM International Conference on, pp. 100-107. IEEE, 2013.




Contact Information:

ITB Journal Publisher, LPPM – ITB, 

Center for Research and Community Services (CRCS) Building Floor 7th, 
Jl. Ganesha No. 10 Bandung 40132, Indonesia,

Tel. +62-22-86010080,

Fax.: +62-22-86010051;

e-mail: jictra@lppm.itb.ac.id.