From: A novel multiple kernel fuzzy topic modeling technique for biomedical data
Method | AC (%) | Precision | Recall | F1-Score | K |
---|---|---|---|---|---|
LSA [5] | 48.36 | 0.4146 | 0.4224 | 0.4185 | 50 |
LDA [4] | 54.10 | 0.4789 | 0.5155 | 0.4970 | 50 |
FKLSA(Entropy) [6] | 75.21 | 0.720 | 0.722 | 0.746 | 50 |
FKLSA(IDF) [6] | 75.90 | 0.722 | 0.723 | 0.746 | 50 |
FKLSA(Normal) [6] | 71.25 | 0.6551 | 0.654 | 0.677 | 50 |
FKLSA(ProbIDF) [6] | 74.87 | 0.715 | 0.714 | 0.735 | 50 |
FKTM [7] | 92.35 | 0.9236 | 0.9006 | 0.9119 | 50 |
MKFTM | 94.10 | 0.9431 | 0.9200 | 0.9213 | 50 |
LSA [5] | 51.37 | 0.4430 | 0.4099 | 0.4258 | 100 |
LDA [4] | 54.92 | 0.4873 | 0.4783 | 0.4828 | 100 |
FKLSA(Entropy) [6] | 76.24 | 0.727 | 0.726 | 0.747 | 100 |
FKLSA(IDF) [6] | 74.35 | 0.701 | 0.703 | 0.726 | 100 |
FKLSA(Normal) [6] | 71.08 | 0.670 | 0.674 | 0.694 | 100 |
FKLSA(ProbIDF) [6] | 74.52 | 0.702 | 0.704 | 0.724 | 100 |
FKTM [7] | 87.70 | 0.8867 | 0.8261 | 0.8553 | 100 |
MKFTM | 89.45 | 0.9063 | 0.8457 | 0.8747 | 100 |
LSA [5] | 52.73 | 0.4651 | 0.4969 | 0.4805 | 150 |
LDA [4] | 57.10 | 0.5123 | 0.5155 | 0.5139 | 150 |
FKLSA(Entropy) [6] | 74.87 | 0.715 | 0.714 | 0.735 | 150 |
FKLSA(IDF) [6] | 76.59 | 0.732 | 0.731 | 0.752 | 150 |
FKLSA(Normal) [6] | 72.46 | 0.671 | 0.673 | 0.691 | 150 |
FKLSA(ProbIDF) [6] | 75.04 | 0.715 | 0.712 | 0.735 | 150 |
FKTM [7] | 90.16 | 0.8788 | 0.9006 | 0.8896 | 150 |
MKFTM | 92.91 | 0.8984 | 0.9203 | 0.9092 | 150 |
LSA [5] | 49.73 | 0.4303 | 0.4410 | 0.4356 | 200 |
LDA [4] | 54.37 | 0.4819 | 0.4969 | 0.4893 | 200 |
FKLSA(Entropy) [6] | 75.21 | 0.720 | 0.721 | 0.740 | 200 |
FKLSA(IDF) [6] | 74.18 | 0.705 | 0.704 | 0.725 | 200 |
FKLSA(Normal) [6] | 71.94 | 0.671 | 0.673 | 0.683 | 200 |
FKLSA(ProbIDF) [6] | 74.87 | 0.701 | 0.702 | 0.729 | 200 |
FKTM [7] | 88.25 | 0.8986 | 0.8261 | 0.8608 | 200 |
MKFTM | 90.35 | 0.9182 | 0.8460 | 0.8802 | 200 |