High Efficiency Spam Filtering: A Manifold Learning-Based Approach

Table 3

Time consumption for different algorithms.

Datasets	SVM [19]	SVM [18]	SVM + LEP	SVM + LEP + Struc
EnronSpam	3523 s	2582 s	983 s	1312 s
PU1	743 s	642 s	236 s	285 s
GenSpam	2452 s	1834 s	634 s	715 s