Big Data Management and Analytics in Scientific Programming: A Deep Learning-Based Method for Aspect Category Classification of Question-Answering-Style Reviews

Table 5

Accuracy and Macro-F1 on the aspect category classification task on QA-style reviews with various sentence numbers in the Bag domain.

Answer	Question
	1		2		3		4
	Accuracy	F1	Accuracy	F1	Accuracy	F1	Accuracy	F1
1	—	—	0.654	0.562	0.648	0.558	0.631	0.551
2	0.664	0.603	0.712	0.624	0.659	0.560	0.641	0.558
3	0.689	0.606	0.668	0.591	0.666	0.598	0.659	0.577
4	0.701	0.619	0.671	0.594	0.664	0.574	0.661	0.583