Biomedical Text Categorization Based on Ensemble Pruning and Optimized Topic Modelling

Table 11

Two-way ANOVA test results of classification accuracy values.

Statistical analysis of results on different LDA-based configurations
Source	DF	SS	MS	F	P
Configuration	23	4073.9	177.1	90.50	P<0.001
Dataset	4	60336.7	15084.2	7707.50	P<0.001
Classifier	1	881.0	881.0	450.15	P<0.001
ConfigurationDataset	92	334.0	3.6	1.85	P<0.001
ConfigurationClassifier	23	932.9	40.6	20.73	P<0.001
DatasetClassifier	4	106.3	26.6	13.57	P<0.001
Error	92	180.1	2.0
Total	239	66844.8
Statistical analysis of results on classifiers and ensemble pruning methods (with LDA (k=50) based representation).
Source	DF	SS	MS	F	P
Configuration	17	2691.7	158.34	25.86	P<0.001
Dataset	4	23128.7	5782.17	944.48	P<0.001
Error	68	416.3	6.12
Total	89
Statistical analysis of results on conventional classifiers, ensemble learners, and ensemble pruning methods (with BA-LDA (DB) based representation).
Source	DF	SS	MS	F	P
Configuration	13	324.5	24.96	17.81	P<0.001
Dataset	4	14736.0	3684.00	2628.98	P<0.001
Error	52	72.9	1.40
Total	69	15133.4