Skip to main content

Table 8 The feature sets used in each performed experiment with the total number of features

From: Classification feature sets for source code plagiarism detection in Java

Experiment

Description of features

Number of features

Hist4

Original features (8) + structural histogram features (8)

16

PerClass

Original features (8) + lexical per-class features (3)

11

Hist4+PerClass

Original features (8) + structural histogram features (8) + lexical per-class features (3)

19

StructCounts

Original features (8) + structural counting features (12)

20

Hist4+StructCounts

Original features (8) + structural histogram features (8) + structural counting features (12)

28

ModOriginal

Modified original features with main included (8)

8

ModOriginal-MainRmv

Modified original features with main excluded (8)

8