Table 9 The performance for K-mean algorithm for the first situation used the text files with Preprocessing 1.
From: Open source Arabic research paper dataset for natural language processing
# K | Silhouette coefficient (euclidean) | Silhouette coefficient (cosine) | ARI | Davies–Bouldin Index |
|---|---|---|---|---|
2 | 0.023 | 0.040 | 0.031 | 3.626 |
3 | 0.042 | 0.076 | 0.073 | 3.659 |
4 | 0.033 | 0.060 | 0.078 | 3.370 |
5 | 0.047 | 0.087 | 0.245 | 5.595 |
6 | 0.046 | 0.084 | 0.266 | 5.906 |
7 | 0.053 | 0.097 | 0.371 | 5.175 |
8 | 0.029 | 0.054 | 0.306 | 4.550 |
9 | 0.037 | 0.068 | 0.419 | 5.123 |
10 | 0.013 | 0.019 | 0.070 | 1.866 |
