[Retracted] An Automated Approach for the Prediction of the Severity Level of Bug Reports Using GPT-2

Table 3

Comparative analysis of the proposed method with CNN, LSTM, NB, RF, and SVM.

Classifier	Accuracy (%)	Precision (%)	Recall (%)	F1-score (%)
Proposed method (based on GPT-2)	91.41	93.00	91.00	91.00
CNN	75.74	58.93	57.32	54.91
LSTM	81.18	70.15	71.48	75.88
NB	50.73	45.54	42.74	47.31
RF	90.71	89.22	88.11	89.55
SVM	52.89	47.34	45.55	48.45