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 realworld datasets show that the proposed method outperforms the state-of-the-art approaches.

Original languageEnglish (US)
Title of host publicationProceedings of the 11th International Conference on Web and Social Media, ICWSM 2017
PublisherAAAI Press
Pages319-326
Number of pages8
ISBN (Electronic)9781577357889
StatePublished - 2017
Event11th International Conference on Web and Social Media, ICWSM 2017 - Montreal, Canada
Duration: May 15 2017May 18 2017

Other

Other11th International Conference on Web and Social Media, ICWSM 2017
CountryCanada
CityMontreal
Period5/15/175/18/17

Fingerprint

Spamming
Costs

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Wu, L., Hu, X., Morstatter, F., & Liu, H. (2017). Adaptive spammer detection with sparse group modeling. In Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017 (pp. 319-326). AAAI Press.

Adaptive spammer detection with sparse group modeling. / Wu, Liang; Hu, Xia; Morstatter, Fred; Liu, Huan.

Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017. AAAI Press, 2017. p. 319-326.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, L, Hu, X, Morstatter, F & Liu, H 2017, Adaptive spammer detection with sparse group modeling. in Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017. AAAI Press, pp. 319-326, 11th International Conference on Web and Social Media, ICWSM 2017, Montreal, Canada, 5/15/17.
Wu L, Hu X, Morstatter F, Liu H. Adaptive spammer detection with sparse group modeling. In Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017. AAAI Press. 2017. p. 319-326
Wu, Liang ; Hu, Xia ; Morstatter, Fred ; Liu, Huan. / Adaptive spammer detection with sparse group modeling. Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017. AAAI Press, 2017. pp. 319-326
@inproceedings{8e255e285c7a4147ba67bcd45d24fa72,
title = "Adaptive spammer detection with sparse group modeling",
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 realworld datasets show that the proposed method outperforms the state-of-the-art approaches.",
author = "Liang Wu and Xia Hu and Fred Morstatter and Huan Liu",
year = "2017",
language = "English (US)",
pages = "319--326",
booktitle = "Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017",
publisher = "AAAI Press",

}

TY - GEN

T1 - Adaptive spammer detection with sparse group modeling

AU - Wu, Liang

AU - Hu, Xia

AU - Morstatter, Fred

AU - Liu, Huan

PY - 2017

Y1 - 2017

N2 - 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 realworld datasets show that the proposed method outperforms the state-of-the-art approaches.

AB - 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 realworld datasets show that the proposed method outperforms the state-of-the-art approaches.

UR - http://www.scopus.com/inward/record.url?scp=85029437735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029437735&partnerID=8YFLogxK

M3 - Conference contribution

SP - 319

EP - 326

BT - Proceedings of the 11th International Conference on Web and Social Media, ICWSM 2017

PB - AAAI Press

ER -