Annotating and detecting topics in social media forum and modelling the annotation to derive directions-a case study

Journal of Big Data

Table 7 Precision, recall and F1-scores of deep learning algorithms

Models	20% of test data from semi-supervised labelled data				20% of test data from manually labelled data
	Precision	Recall	F1-Score	Accuracy	Precision	Recall	F1-Score	Accuracy
CNN	0.751	0.773	0.762	0.757	0.756	0.768	0.759	0.760
LSTM	0.780	0.789	0.784	0.782	0.779	0.791	0.789	0.786
BiLSTM	0.792	0.790	0.791	0.797	0.795	0.789	0.793	0.795