Adaptive Spammer Detection with Sparse Group Modeling

Liang Wu, Xia Hu, Fred Morstatter, Huan Liu

Abstract

Social media platforms face an ongoing battle against evolving spamming tactics. Traditional detection methods often fail to account for the varying organizational scales of spammers, from large botnets to independent actors. This paper presents SGASD (Sparse Group Modeling for Adaptive Spammer Detection), a framework that utilizes a hierarchical index tree and sparse learning to adaptively identify suspicious group structures. By combining social network analysis with message content, SGASD achieves superior detection performance and robustness, particularly in identifying spammers that operate outside of dense clusters.

Introduction

Spammer detection typically relies on link-based, neighbor-based, or group-based analysis. However, modern spammers employ "link farming" to deceive these models and vary their group sizes to avoid detection. The core challenge lies in determining the optimal group granularity—identifying whether a spammer is part of a small cell, a massive network, or acting alone. Existing methods often struggle with this variance, either focusing too narrowly on individuals or too broadly on fixed clusters.

Methodology

The SGASD framework addresses these challenges by treating spammer detection as a sparse learning task. It employs Adaptive Group Structure Modeling, using the Louvain method to construct a hierarchical index tree. This tree represents users at multiple resolutions, from individual leaf nodes to small clusters and large root communities.

Hierarchical index tree representing users at multiple resolutions for adaptive group modeling.

To isolate relevant groups, the model applies a Sparse Group Selection mechanism using a group lasso-style penalty ($\ell_{1,2}$-norm). This mathematical constraint filters out noise and focuses on the most discriminative structures. Furthermore, SGASD integrates message content analysis with network structure through an integrated objective function, optimized via Stochastic Gradient Descent (SGD) for scalability on large-scale social media data.

Results and Insights

The model was evaluated on two Twitter datasets: TwitterS (suspended accounts, 7.5% spammers) and TwitterH (honeypot accounts, 50% spammers). SGASD consistently outperformed state-of-the-art baselines, achieving an $F_1$ score of 88.01% on TwitterS and 95.31% on TwitterH.

A key advantage of SGASD is its ability to detect "sparse" spammers. While baseline methods like SSDM primarily identify spammers in dense, obvious clusters, SGASD's hierarchical approach allows it to find spammers in sparse areas of the feature space—the so-called "lone wolves" who detach from groups to avoid detection.

PCA visualization comparing SGASD and SSDM in identifying spammers across dense and sparse feature spaces.

Conclusion

SGASD provides a robust and scalable solution for large-scale spammer detection by adaptively modeling social structures. By leveraging sparsity as a filter and integrating content with network data, it effectively addresses the limitations of fixed-granularity models. Future work will explore incorporating heterogeneous data sources like timestamps and location data to further enhance detection accuracy against increasingly subtle spamming tactics.

Summary updated

Abstract

Social spammers disseminate unsolicited information on social media sites that negatively impacts social networking systems. To detect social spammers, traditional methods leverage social network structures to identify the behavioral patterns hidden in their social interactions. They focus on accounts that are affiliated with groups comprising known spammers. However, since different parties are emerging to generate various spammers, they may form different kinds of groups, and some spammers may even detach from the flock. Therefore, it is challenging for existing methods to find the optimal group structure that captures different spammers simultaneously. Employing different approaches for specific spammers is time-consuming, and it also lacks the adaptivity of dealing with emerging spammers. In this work, we aim to propose a group modeling framework that adaptively characterizes social interactions of spammers. In particular, we introduce to integrate content information into the group modeling process. The proposed framework exploits additional content information in selecting groups and individuals that are likely to be involved in spamming activities. In order to alleviate the intensive computational cost, we transform the problem as a sparse learning task that can be solved efficiently. Experimental results on real-world datasets show that the proposed method outperforms the state-of-the-art approaches.
BibTeX
@inproceedings{wu2017adaptive,
  author = {Liang Wu and Xia Hu and Fred Morstatter and Huan Liu},
  title = {{Adaptive Spammer Detection with Sparse Group Modeling}},
  booktitle = {ICWSM},
  year = {2017},
}

Loading related content...

Figure