A Deep-Learning Framework for Analysing Students’ Review in Higher Education

Table 9

Comparison of proposed approach in this work with state-of-the-art performance for sentiment polarity.

	Bi-LSTM-ANN			Baseline
	P	R	F1	P	R	F1
A	0.96	0.59	0.73	0.78	0.74	0.76
B	0.44	0.82	0.58	0.45	0.54	0.49
C	0.47	0.50	0.48	0.33	0.46	0.38
D	0.38	0.22	0.28	0.50	0.30	0.37
F	1.00	0.69	0.82	1.00	0.76	0.86
Accuracy			0.59			0.57
Macro average	0.65	0.56	0.58	0.61	0.56	0.57
Weighted average	0.66	0.59	0.59	0.61	0.57	0.58