Table 15 The performance for K-mean algorithm for the last situation Preprocessing 3.

From: Open source Arabic research paper dataset for natural language processing

# K

Silhouette coefficient (euclidean)

Silhouette coefficient (cosine)

ARI

Davies–Bouldin Index

2

0.052

0.097

0.061

3.363

3

0.048

0.087

0.108

3.615

4

0.041

0.074

0.113

4.032

5

0.056

0.103

0.356

4.957

6

0.055

0.100

0.322

4.292

7

0.047

0.087

0.399

4.397

8

0.036

0.067

0.451

4.296

9

0.044

0.080

0.494

4.618

10

0.039

0.071

0.420

4.174