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

Algorithm 1

Pseudocode of the proposed methodology.

	Begin:
	Preprocessing of extracted data
	Input: Statements S extracted from N Bug reports.
(a)	Removal of A = stop words from Statements S
(b)	Removal of P = punctuation from Statements S
(c)	Perform word stemming () in the statements S
	Calculate emotion score E using senti4SD
	Calculate word embedding for each vector using the equation:
	Where, T is length of text sequence, and .
	Pass the embedded vectors to the classifier GPT-2 such that:
	T = training data
	X = pool of examples by choosing randomly
	For i = 0 to K
	Use T for training the classifier, 80%
	Use remaining 20% of T to test the classifier
	End for end