Table 2. Sentiment distributions of the application datasets as predicted by the sentiment classifiers.

The rightmost column shows the sentiment score (the mean) of the application and training datasets (the later from Table 1), respectively.

					Sentiment score
Dataset	Negative	Neutral	Positive	Total	application	training
Facebook(it)	466,292	435,641	115,576	1,017,509	−0.345	−0.293
DJIA30	139,132	1,141,563	275,075	1,555,770	+0.087	+0.079
Environment	470,953	2,172,394	519,688	3,163,035	+0.015	−0.137