Social spam detection
Authors:
Open Access
- 21 April 2009
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 41-48
Abstract
The popularity of social bookmarking sites has made them prime targets for spammers. Many of these systems require an adminis- trator's time and energy to manually filter or remove spam. Here we discuss the motivations of social spam, and present a study of automatic detection of spammers in a social tagging system. We identify and analyze six distinct features that address various properties of social spam, finding that each of these features pro- vides for a helpful signal to discriminate spammers from legitimate users. These features are then used in various machine learning algorithms for classification, achieving over 98% accuracy in de- tecting social spammers with 2% false positives. These promising results provide a new baseline for future efforts on social spam. We make our dataset publicly available to the research community.Keywords
This publication has 15 references indexed in Scilit:
- A few bad votes too many?2008
- Cleaning search results using term distance features2008
- Semantic Grounding of Tag Relatedness in Social Bookmarking Systems2008
- Fighting Spam on Social Web Sites: A Survey of Approaches and Future ChallengesIEEE Internet Computing, 2007
- Combating spam in tagging systems2007
- Usage patterns of collaborative tagging systemsJournal of Information Science, 2006
- Collaborative Tagging as a Tripartite NetworkLecture Notes in Computer Science, 2006
- Information Retrieval in Folksonomies: Search and Ranking2006
- Ontologies Are Us: A Unified Model of Social Networks and Semantics2005
- Syntactic clustering of the WebComputer Networks and ISDN Systems, 1997