Loading...

DWM-CDD: Dynamic weighted majority concept drift detection for spam mail filtering

Nosrati, L ; Sharif University of Technology

709 Viewed
  1. Type of Document: Article
  2. Abstract:
  3. Although e-mail is the most efficient and popular communication method, unwanted and mass unsolicited e-mails, also called spam mail, endanger the existence of the mail system. This paper proposes a new algorithm called Dynamic Weighted Majority Concept Drift Detection (DWM-CDD) for content-based filtering. The design purposes of DWM-CDD are first to accurate the performance of the previously proposed algorithms, and second to speed up the time to construct the model. The results show that DWM-CDD can detect both sudden and gradual changes quickly and accurately. Moreover, the time needed for model construction is less than previously proposed algorithms
  4. Keywords:
  5. Concept drift ; E-mail ; Spam mail ; Communication method ; Concept drifts ; Content-based filtering ; Gradual changes ; Model construction ; Spam mails ; Speed-ups ; Content based filtering ; Algorithms ; Content based retrieval ; Internet ; Electronic mail
  6. Source: World Academy of Science, Engineering and Technology ; Volume 80 , 2011 , Pages 291-294 ; 2010376X (ISSN)