Hybrid support vector machine and K‐nearest neighbor‐based software testing for educational assistant

Abstract

In terms of training students for work in diverse firms, traditional and out-of-date teaching techniques cannot compete with digital teaching methods. To overcome this problem, the teaching approach and content must be changed. An Educational Assistant for Software Testing (EAST) framework is developed in this work to train students to improve their skills in software testing via Computer Assisted Instruction (CAI) built using Natural Language Processing (NLP), Machine learning, and information retrieval techniques. In this paper, a Group Search Optimized two-stage hybrid Support Vector Machine-K-Nearest Neighbor (SVM-KNN) classifier is used to develop a novel approach for analyzing the parameters that introduce bugs in bug reports. To decrease the data sparsity problem, the group search optimization (GSO) algorithm is used to improve the parameter selection process of the two-stage hybrid classifier by generating optimal values for parameters such as k, c, and gamma. Two bug report datasets were used to test the model. The database for our application is built by collecting bug reports from a wide open-source community as well as several mobile application development companies. Based on the extensive experiments conducted via different performance metrics, we can conclude that the EAST framework can improve outdated teaching methodologies.

Bug Report Classification with Ensemble Learning for Closed-Source Software

“…They classify bug reports as production or test bug reports. Ramesh et al [13] propose a framework utilizing a group search optimization algorithm and a hybrid SVM-KNN classifier to categorize bug reports. Köksal and Öztürk [26] provide a comprehensive literature review on automated bug report classification.…”

“…Thus, automatic issue/feature classification is a significant problem in software development. Some of the prior works [12,13] in literature utilize traditional ML methods to solve this problem, whereas others [6,14] use more advanced ML algorithms, such as BERT [15] and convolutional neural networks (CNN) [16].…”