SPADE: a social-spam analytics and detection framework

De, Wang; Irani, Danesh; Pu, Calton

doi:10.1007/s13278-014-0189-1

Cited by 19 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To cover deceptive information sharing, two more categories (i. people who lie for representing a good social image and ii. people who lie for malicious intentions) could be added to three categories of information sharing mentioned in [87]: privacy fundamentalist (unwilling to share), pragmatic majority (willing to share with privacy control), and marginally concerned (willing to share). Then it would be good if these five groups of people could be linked to behavioral models.…”

Section: Discussionmentioning

confidence: 99%

“…Even though there are some analysis tools and filtering techniques, most of the time it is not enough to prevent such spams. Thus, it is crucial to find the spam messages and spammers by creating features such as shown in Tables 2-3 and using machine learning techniques [78,87]. Creating honeypots and fake accounts may also be used to attract the spammers and then to find the creators of these accounts (spammers) [78,91].…”

Section: User Categorizationmentioning

confidence: 99%

“…This yields 17,000 spammer accounts collected with 60% accuracy. Wang et al [87] propose a framework called SPADE in order to detect spam messages and spammers using 15 and 74 attributes, respectively. As a result, over 0.92 F-measure and 91% detection accuracy on web page model (in cross domain classification), 0.87 F-measure on user profile model, and 0.89 F-measure on message models are achieved by SPADE.…”

Section: Overviewmentioning

confidence: 99%

See 2 more Smart Citations

User characterization for online social networks

Tuna

Akbaş

Aksoy

et al. 2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Online social network analysis has attracted great attention with a vast number of users sharing information and availability of APIs that help to crawl online social network data. In this paper, we study the research studies that are helpful for user characterization as online users may not always reveal their true identity or attributes. We especially focused on user attribute determination such as gender, age, etc.; user behavior analysis such as motives for deception; mental models that are indicators of user behavior; user categorization such as bots vs. humans; and entity matching on different social networks. We believe our summary of analysis of user characterization will provide important insights to researchers and better services to online users

show abstract

Section: Discussionmentioning

confidence: 99%

Section: User Categorizationmentioning

confidence: 99%

Section: Overviewmentioning

confidence: 99%

See 1 more Smart Citation

User characterization for online social networks

Tuna

Akbaş

Aksoy

et al. 2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…In this regard, there are only a few web spam corpora publicly available that can be successfully used to train, test, compare and rank existing and novel approaches for effective web spam detection and filtering. Moreover, most of the available alternatives are outdated and distributed in different incompatible formats [ 8 , 9 , 11 , 18 , 19 , 23 , 26 , 28 , 29 , 30 , 31 , 32 ]. This situation forces research teams to always carry out a previous compulsory task of data preparation and preprocessing [ 29 ], which in web spam-filtering domain habitually becomes hard, costly, time consuming and prone to error.…”

Section: Introductionmentioning

confidence: 99%

WARCProcessor: An Integrative Tool for Building and Management of Web Spam Corpora

Callón

Fdez-Glez²,

Ruano-Ordás

et al. 2017

Sensors

View full text Add to dashboard Cite

In this work we present the design and implementation of WARCProcessor, a novel multiplatform integrative tool aimed to build scientific datasets to facilitate experimentation in web spam research. The developed application allows the user to specify multiple criteria that change the way in which new corpora are generated whilst reducing the number of repetitive and error prone tasks related with existing corpus maintenance. For this goal, WARCProcessor supports up to six commonly used data sources for web spam research, being able to store output corpus in standard WARC format together with complementary metadata files. Additionally, the application facilitates the automatic and concurrent download of web sites from Internet, giving the possibility of configuring the deep of the links to be followed as well as the behaviour when redirected URLs appear. WARCProcessor supports both an interactive GUI interface and a command line utility for being executed in background.

show abstract

“…It implements algorithms for regression, classification, clustering, association rule mining and attribute selection. With all these features, Weka is widely used in business (Hailemariam et al 2012), research (Zhu et al 2014;Fire et al 2014;Wang et al 2014) and education (Markov and Russell 2006).…”

Section: Introductionmentioning

confidence: 99%

Performance improvement of data mining in Weka through multi-core and GPU acceleration: opportunities and pitfalls

Engel

Charão

Kirsch-Pinheiro

et al. 2015

J Ambient Intell Human Comput

View full text Add to dashboard Cite

International audienceData mining tools may be computationally demanding, which leads to an increasing interest on par- allel computing strategies in order to improve their per- formance. While multi-core processors and Graphics Processing Units (GPUs) accelerators increased the com- puting power of current desktop computers, we observe that desktop-based data mining tools do not take full advantage of these architectures yet. This paper investi- gates strategies to improve the performance of Weka, a popular data mining tool, through multi-core and GPU acceleration. Using performance profiling of Weka, we identify operations that could improve the data mining performance when parallelized. We selected two of these operations, and analyze the impact of their parallel exe- cution on Weka’s performance. These experiments demonstrate that while significant speedups can be achieved, all operations are not prone to be parallelized, which reinforces the need for a careful and well-studied selection of the candidates

show abstract

SPADE: a social-spam analytics and detection framework

Cited by 19 publications

References 36 publications

User characterization for online social networks

User characterization for online social networks

WARCProcessor: An Integrative Tool for Building and Management of Web Spam Corpora

Performance improvement of data mining in Weka through multi-core and GPU acceleration: opportunities and pitfalls

Contact Info

Product

Resources

About