• We propose a graph neural network-based model for long method and blob code smell detection. • The best strategies for the class imbalance of graph data and graph pooling are determined through experiments in our method. • During model design for abstract syntax tree of code, Euclidean space and non-Euclidean space are combined. • The experiments show that our proposed method outperforms machine learning methods and deep learning methods. The concept of code smell was first proposed in the late nineties, to refer to signals that code may need refactoring. While not necessarily affecting functionality, code smell can hinder understandability and future scalability of the program. As a result, the precise detection of code smell has become an important topic in coding research. However, current detection methods are limited by imbalanced and industrial-irrelevant datasets, a lack of sufficient structural and logical information on the code, and simple model architecture. Given these limitations, this paper utilized an industry-relevant and sufficient dataset and then developed a graph neural network to better detect code smell. First, we identified Long Method and Blob as our research subjects due to their frequent occurrence and impacts on the maintainability of software. We then designed modified fuzzy sampling with focalloss to address the issue of data imbalance. Second, to deal with the large volume of data, we proposed a global and local attention scoring mechanism to extract the key information from the code. Third, in order to design a graph neural network specifically for the abstract syntax tree of code, we combined Euclidean space and non-Euclidean space. Finally, we compared our method with other machine learning methods and deep learning methods. The results demonstrate that our method outperforms the other methods on Long Method and Blob, which indicates the effectiveness of our proposed method.

Transfer learning techniques have been proved to be effective in the field of Cross-project defect prediction (CPDP). However, some questions still remain. First, the conditional distribution difference between source and target projects has not been considered. Second, facing multiple source projects, most studies only rarely consider the issues of source selection and multi-source data utilization; instead, they use all available projects and merge multi-source data together to obtain one final dataset. To address these issues, in this paper, we propose a three-stage weighting framework for multi-source transfer learning (3SW-MSTL) in CPDP. In stage 1, a source selection strategy is needed to select a suitable number of source projects from all available projects. In stage 2, a transfer technique is applied to minimize marginal differences. In stage 3, a multi-source data utilization scheme that uses conditional distribution information is needed to help guide researchers in the use of multi-source transferred data. First, we have designed five source selection strategies and four multi-source utilization schemes and chosen the best one to be used in stage 1 and 3 in 3SW-MSTL by comparing their influences on prediction performance. Second, to validate the performance of 3SW-MSTL, we compared it with four multi-source and six single-source CPDP methods, a baseline within-project defect prediction (WPDP) method, and two unsupervised methods on the data from 30 widely used open-source projects. Through experiments, bellwether and weighted vote are separately chosen as a source selection strategy and a multi-source utilization scheme used in 3SW-MSTL. And, our results indicate that 3SW-MSTL outperforms four multi-source, six single-source CPDP methods and two unsupervised methods. And, 3SW-MSTL is comparable to the WPDP method. The proposed 3SW-MSTL model is more effective for considering the two issues mentioned before.

As software systems are becoming more pervasive, they are also becoming more susceptible to failures, resulting in potentially lethal combinations. Software testing is critical to preventing software failures but is, arguably, the least understood part of the software life cycle and the toughest to perform correctly. Adequate research has been carried out in both the process and technology dimensions of testing, but not in the human dimensions. This paper attempts to fill in the gap by exploring the human dimension, i.e., trying to understand the motivation of software professionals to take up and sustain testing careers. Towards that end, a survey was conducted in four countries - India, Canada, Cuba, and China - to try to understand how professional software testers perceive and value work-related factors that could influence their motivation to take up and sustain testing careers. With a sample of 220 software professionals, we observed that very few professionals are keen to take up testing careers. Some aspects of software testing, such as the learning opportunities, appear to be a common motivator across the four countries; whereas the treatment meted out to testers as second-class citizens and the complexity of the job appeared to be the most important de-motivators. This comparative study offers useful insights that can help global software industry leaders to come up with an action plan to put the software testing profession under a new light. That could increase the number of software engineers choosing testing careers, which would facilitate quality testing.

Abstract An individual's decision‐making behavior is heavily influenced by and adapted to external environmental factors. Given that software development is a human‐centered activity, individual decision‐making behavior may affect the software project quality. Although environmental factors affecting decision‐making behavior in software projects have been identified in prior literature, there is not yet an objective and a full taxonomy of these factors. Thus, it is not trivial to manage these complex and diverse factors. To address this deficiency, we first design a semantic similarity algorithm between words by utilizing the synonymy and hypernymy relationships in WordNet. Further, we propose a method to measure semantic similarity between phrases and apply it into k‐means clustering algorithm to group these factors. Subsequently, we obtain a taxonomy of the environmental factors affecting individual decision‐making behavior in software projects, which includes 11 broad categories, each containing 2 to 5 sub‐categories. The taxonomy presented herein is obtained by an objective method, and quite comprehensive, with appropriate references provided. The taxonomy holds significant value for researchers and practitioners; it can help them to better understand the major aspects of environmental factors, also to predict and guide the behavior of individuals during decision making towards a successful completion of software projects.