From: A set theory based similarity measure for text clustering and classification
No | Dataset | Reuters | Web-KB | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Similarity/criterion | ACC | PRE | REC | FM | GM | AMP | ACC | PRE | REC | FM | GM | AMP | |
1 | Euclidean | 0.615 | 0.716 | 0.294 | 0.344 | 0.510 | 0.271 | 0.550 | 0.768 | 0.428 | 0.422 | 0.591 | 0.384 |
2 | Cosine | 0.897 | 0.903 | 0.716 | 0.767 | 0.836 | 0.650 | 0.766 | 0.803 | 0.670 | 0.715 | 0.799 | 0.614 |
3 | Jaccard | 0.865 | 0.813 | 0.550 | 0.601 | 0.730 | 0.488 | 0.786 | 0.859 | 0.684 | 0.694 | 0.792 | 0.619 |
4 | Bhattacharya | 0.888 | 0.867 | 0.683 | 0.693 | 0.818 | 0.590 | 0.534 | 0.689 | 0.526 | 0.434 | 0.667 | 0.406 |
5 | kullback–Leibler | 0.503 | 0.164 | 0.128 | 0.089 | 0.335 | 0.128 | 0.134 | 0.079 | 0.248 | 0.090 | 0.431 | 0.250 |
6 | Manhattan | 0.527 | 0.376 | 0.162 | 0.144 | 0.373 | 0.158 | 0.429 | 0.669 | 0.294 | 0.220 | 0.474 | 0.284 |
7 | PDSM | 0.909 | 0.899 | 0.700 | 0.745 | 0.827 | 0.631 | 0.801 | 0.854 | 0.714 | 0.727 | 0.812 | 0.642 |
8 | STB-SM | 0.912 | 0.913 | 0.739 | 0.783 | 0.851 | 0.676 | 0.791 | 0.841 | 0.706 | 0.715 | 0.806 | 0.630 |