Facebook is one of the most popular and leading social network services online. With the increasing amount of users on Facebook, the probability of broadcasting spam content on it is also escalating day by day. There are a few existing techniques to combat spam on Facebook. However, due to the public unavailability of critical pieces of Facebook information, like profiles, network information, an unlimited number of posts and more, the existing techniques do not work efficiently for detecting many spammers. In this paper, we propose an efficient spammer detection framework (we called as SpamSpotter) that distinguishes spammers from legitimate users on Facebook. Based on Facebook's recent characteristics, the framework introduces a novel feature set to facilitate spammer detection. We use a baseline dataset from Facebook that included 300 spammers and 700 legitimate user profiles. The baseline dataset contains a set of features for each profile, which are extracted using a novel dataset construction mechanism. In addition, an intelligent decision support system that uses eight different machine learning classifiers on the baseline dataset is designed to distinguish spammers from legitimate users. To evaluate the efficiency and accuracy of our proposed framework, we implemented and compared it with existing frameworks. The evaluation results demonstrate that our proposed framework is accurate and efficient to deliver first-rate performance. It attains a higher accuracy of 0.984 and Mathew correlation coefficient of 0.977.

SpamSpotter: An efficient spammer detection framework based on intelligent decision support system on Facebook

Loia V.;
2018-01-01

Abstract

Facebook is one of the most popular and leading social network services online. With the increasing amount of users on Facebook, the probability of broadcasting spam content on it is also escalating day by day. There are a few existing techniques to combat spam on Facebook. However, due to the public unavailability of critical pieces of Facebook information, like profiles, network information, an unlimited number of posts and more, the existing techniques do not work efficiently for detecting many spammers. In this paper, we propose an efficient spammer detection framework (we called as SpamSpotter) that distinguishes spammers from legitimate users on Facebook. Based on Facebook's recent characteristics, the framework introduces a novel feature set to facilitate spammer detection. We use a baseline dataset from Facebook that included 300 spammers and 700 legitimate user profiles. The baseline dataset contains a set of features for each profile, which are extracted using a novel dataset construction mechanism. In addition, an intelligent decision support system that uses eight different machine learning classifiers on the baseline dataset is designed to distinguish spammers from legitimate users. To evaluate the efficiency and accuracy of our proposed framework, we implemented and compared it with existing frameworks. The evaluation results demonstrate that our proposed framework is accurate and efficient to deliver first-rate performance. It attains a higher accuracy of 0.984 and Mathew correlation coefficient of 0.977.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11386/4759112
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 56
  • ???jsp.display-item.citation.isi??? 42
social impact