Table 12 The performance for K-mean algorithm for the second situation Preprocessing 2.

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

# K

Silhouette coefficient (euclidean)

Silhouette coefficient (cosine)

ARI

Davies–Bouldin Index

2

0.045

0.083

0.059

3.450

3

0.046

0.083

0.075

3.580

4

0.049

0.089

0.174

4.784

5

0.052

0.094

0.291

5.486

6

0.045

0.082

0.347

5.353

7

0.052

0.095

0.446

5.019

8

0.055

0.101

0.394

5.269

9

0.054

0.098

0.490

4.635

10

0.043

0.078

0.483

4.774