Deep Learning- and Word Embedding-Based Heterogeneous Classifier Ensembles for Text Classification

Table 1

Number of classes (), documents (), and words () in each document.

Dataset
20News-18828	20	18,828	50,570
20News-19997	20	19,997	43,553
Mini-news	20	2000	13,943
WebKB4	4	4199	16,116
1150haber	5	1150	11,040
Milliyet	9	9000	63,371
Hurriyet	8	6000	18,280
Aahaber	8	2000	14,396