Multiple Accounts Detection on Facebook Using Semi-Supervised Learning on Graphs

TL;DR

This paper presents a semi-supervised graph embedding approach to detect multiple accounts created by the same user on Facebook, achieving high accuracy and AUC in diverse datasets.

Contribution

It introduces a novel semi-supervised learning method using graph embeddings for account matching, emphasizing local information importance and optimal threshold determination.

Findings

Achieved 0.996 accuracy and 0.952 AUC on Middle East Facebook data.

Obtained 0.877 AUC on U.S. election dataset for different-named accounts.

Local information is more influential than global data for prediction.

Abstract

In social networks, a single user may create multiple accounts to spread his / her opinions and to influence others, by actively comment on different news pages. It would be beneficial to both social networks and their communities, to demote such abnormal activities, and the first step is to detect those accounts. However, the detection is challenging, because these accounts may have very realistic names and reasonable activity patterns. In this paper, we investigate three different approaches, and propose using graph embedding together with semi-supervised learning, to predict whether a pair of accounts are created by the same user. We carry out extensive experimental analyses to understand how changes in the input data and algorithmic parameters / optimization affect the prediction performance. We also discover that local information have higher importance than the global ones for such prediction, and point out the threshold leading to the best results. We test the proposed approach with 6700 Facebook pages from the Middle East, and achieve the averaged accuracy at 0.996 and AUC (area under curve) at 0.952 for users with the same name; with the U.S. 2016 election dataset, we obtain the best AUC at 0.877 for users with different names.