Design and Implementation of a Machine Learning-Based Authorship Identification Model

Table 5

PAN12 datasets used in the experiments.

Dataset	Training documents words	Distinct words	Vocabulary size
A1	25,771	3,252	900
A2	128,845	48,012	1,500
A3	25,771	3,252	900
A4	128,845	48,012	1,500
C1	96,052	26,654	2,400
C2	480,250	133,256	4,000
C3	96,052	26,654	2,400
C4	480,250	133,256	4,000
I1	2,353,267	137,315	4,200
I2	11,766,325	7,839,471	7,000
I3	2,353,267	137,315	4,200
I4	11,766,325	7,839,471	7,000