Requirements Engineering (RE) requires the collaboration of various roles in SE, such as requirements engineers, stakeholders and other developers, and it is thus a highly human dependent process in software engineering (SE). Identifying how human as
pects such as personality, motivation, emotions, communication, gender, culture and geographic distribution might impact RE would assist us in better supporting successful RE. The main objective of this paper is to systematically review primary studies that have investigated the effects of various human aspects on RE. A systematic literature review (SLR) was conducted and identified 474 initial primary research studies. These were eventually filtered down to 74 relevant, high-quality primary studies. Among the studies, the effects of communication have been considered in many RE studies. Other human aspects such as personality, motivation and gender have mainly been investigated to date related to SE studies including RE as one phase. Findings show that studying more than one human aspect together is beneficial, as this reveals relationships between various human aspects and how they together impact the RE process. However, the majority of these studied combinations of human aspects are unique. From 56.8% of studies that identified the effects of human aspects on RE, 40.5% identified the positive impact, 30.9% negative, 26.2% identified both impacts whereas 2.3% mentioned that there was no impact. This implies that a variety of human aspects positively or negatively affects the RE process and a well-defined theoretical analysis on the effects of different human aspects on RE remains to be defined and practically evaluated. Findings of this SLR help researchers who are investigating the impact of various human aspects on RE by identifying well-studied research areas, and highlight new areas that should be focused on in future research.
Machine learning (ML) provides us with numerous opportunities, allowing ML systems to adapt to new situations and contexts. At the same time, this adaptability raises uncertainties concerning the run-time product quality or dependability, such as rel
iability and security, of these systems. Systems can be tested and monitored, but this does not provide protection against faults and failures in adapted ML systems themselves. We studied software designs that aim at introducing fault tolerance in ML systems so that possible problems in ML components of the systems can be avoided. The research was conducted as a case study, and its data was collected through five semi-structured interviews with experienced software architects. We present a conceptualisation of the misbehaviour of ML systems, the perceived role of fault tolerance, and the designs used. Common patterns to incorporating ML components in design in a fault tolerant fashion have started to emerge. ML models are, for example, guarded by monitoring the inputs and their distribution, and enforcing business rules on acceptable outputs. Multiple, specialised ML models are used to adapt to the variations and changes in the surrounding world, and simpler fall-over techniques like default outputs are put in place to have systems up and running in the face of problems. However, the general role of these patterns is not widely acknowledged. This is mainly due to the relative immaturity of using ML as part of a complete software system: the field still lacks established frameworks and practices beyond training to implement, operate, and maintain the software that utilises ML. ML software engineering needs further analysis and development on all fronts.
With the growing capabilities of autonomous vehicles, there is a higher demand for sophisticated and pragmatic quality assurance approaches for machine learning-enabled systems in the automotive AI context. The use of simulation-based prototyping pla
tforms provides the possibility for early-stage testing, enabling inexpensive testing and the ability to capture critical corner-case test scenarios. Simulation-based testing properly complements conventional on-road testing. However, due to the large space of test input parameters in these systems, the efficient generation of effective test scenarios leading to the unveiling of failures is a challenge. This paper presents a study on testing pedestrian detection and emergency braking system of the Baidu Apollo autonomous driving platform within the SVL simulator. We propose an evolutionary automated test generation technique that generates failure-revealing scenarios for Apollo in the SVL environment. Our approach models the input space using a generic and flexible data structure and benefits a multi-criteria safety-based heuristic for the objective function targeted for optimization. This paper presents the results of our proposed test generation technique in the 2021 IEEE Autonomous Driving AI Test Challenge. In order to demonstrate the efficiency and effectiveness of our approach, we also report the results from a baseline random generation technique. Our evaluation shows that the proposed evolutionary test case generator is more effective at generating failure-revealing test cases and provides higher diversity between the generated failures than the random baseline.
Requirements Engineering (RE) is a process that requires high collaboration between various roles in software engineering (SE), such as requirements engineers, stakeholders, developers, etc. Their demographics, views, understanding of technologies, w
orking styles, communication and collaboration capabilities make RE highly human dependent. Identifying how human aspects such as motivation, domain knowledge, communication skills, personality, emotions, culture, etc might impact RE would help us to improve the RE activities and SE in general. The aim of this study is to understand current industry perspectives on the influence of human aspects on RE. We surveyed 111 software practitioners involved in RE activities, and our findings show that 86.4% of participants agree, that the success of RE greatly depends on the people involved in it. Software practitioners consider motivation, domain knowledge, attitude, communication skills and personality as highly important human aspects when involved in RE. A set of factors, we categorize as human/social and technical were identified as software practitioners motivation factors when involved in RE activities, where the majority of are motivated due to human/social factors. Furthermore, our findings suggest that software practitioners personality characteristics should also be paid more attention to as they are important when conducting RE effectively.
Context: software projects are common resources in Software Engineering experiments, although these are often selected without following a specific strategy, which reduces the representativeness and replication of the results. An option is the use of
preserved collections of software projects, but these must be current, with explicit guidelines that guarantee their updating over a long period of time. Goal: to carry out a systematic secondary study about the strategies to select software projects in empirical studies to discover the guidelines taken into account, the degree of use of project collections, the meta-data extracted and the subsequent statistical analysis conducted. Method: A systematic mapping study to identify studies published from January 2013 to December 2020. Results: 122 studies were identified, of which the 72% used their own guidelines for project selection and the 27% used existent project collections. Likewise, there was no evidence of a standardized framework for the project selection process, nor the application of statistical methods that relates with the sample collection strategy.
Deep Learning (DL) components are routinely integrated into software systems that need to perform complex tasks such as image or natural language processing. The adequacy of the test data used to test such systems can be assessed by their ability to
expose artificially injected faults (mutations) that simulate real DL faults. In this paper, we describe an approach to automatically generate new test inputs that can be used to augment the existing test set so that its capability to detect DL mutations increases. Our tool DeepMetis implements a search based input generation strategy. To account for the non-determinism of the training and the mutation processes, our fitness function involves multiple instances of the DL model under test. Experimental results show that tool is effective at augmenting the given test set, increasing its capability to detect mutants by 63% on average. A leave-one-out experiment shows that the augmented test set is capable of exposing unseen mutants, which simulate the occurrence of yet undetected faults.
Program representation learning is a fundamental task in software engineering applications. With the availability of big code and the development of deep learning techniques, various program representation learning models have been proposed to unders
tand the semantic properties of programs and applied on different software engineering tasks. However, no previous study has comprehensively assessed the generalizability of these deep models on different tasks, so that the pros and cons of the models are unclear. In this experience paper, we try to bridge this gap by systemically evaluating the performance of eight program representation learning models on three common tasks, where six models are based on abstract syntax trees and two models are based on plain text of source code. We kindly explain the criteria for selecting the models and tasks, as well as the method for enabling end-to-end learning in each task. The results of performance evaluation show that they perform diversely in each task and the performance of the AST-based models is generally unstable over different tasks. In order to further explain the results, we apply a prediction attribution technique to find what elements are captured by the models and responsible for the predictions in each task. Based on the findings, we discuss some general principles for better capturing the information in the source code, and hope to inspire researchers to improve program representation learning methods for software engineering tasks.
Collaborative live chats are gaining popularity as a development communication tool. In community live chatting, developers are likely to post issues they encountered (e.g., setup issues and compile issues), and other developers respond with possible
solutions. Therefore, community live chats contain rich sets of information for reported issues and their corresponding solutions, which can be quite useful for knowledge sharing and future reuse if extracted and restored in time. However, it remains challenging to accurately mine such knowledge due to the noisy nature of interleaved dialogs in live chat data. In this paper, we first formulate the problem of issue-solution pair extraction from developer live chat data, and propose an automated approach, named ISPY, based on natural language processing and deep learning techniques with customized enhancements, to address the problem. Specifically, ISPY automates three tasks: 1) Disentangle live chat logs, employing a feedforward neural network to disentangle a conversation history into separate dialogs automatically; 2) Detect dialogs discussing issues, using a novel convolutional neural network (CNN), which consists of a BERT-based utterance embedding layer, a context-aware dialog embedding layer, and an output layer; 3) Extract appropriate utterances and combine them as corresponding solutions, based on the same CNN structure but with different feeding inputs. To evaluate ISPY, we compare it with six baselines, utilizing a dataset with 750 dialogs including 171 issue-solution pairs and evaluate ISPY from eight open source communities. The results show that, for issue-detection, our approach achieves the F1 of 76%, and outperforms all baselines by 30%. Our approach achieves the F1 of 63% for solution-extraction and outperforms the baselines by 20%.
With the ever-increasing use of web APIs in modern-day applications, it is becoming more important to test the system as a whole. In the last decade, tools and approaches have been proposed to automate the creation of system-level test cases for thes
e APIs using evolutionary algorithms (EAs). One of the limiting factors of EAs is that the genetic operators (crossover and mutation) are fully randomized, potentially breaking promising patterns in the sequences of API requests discovered during the search. Breaking these patterns has a negative impact on the effectiveness of the test case generation process. To address this limitation, this paper proposes a new approach that uses agglomerative hierarchical clustering (AHC) to infer a linkage tree model, which captures, replicates, and preserves these patterns in new test cases. We evaluate our approach, called LT-MOSA, by performing an empirical study on 7 real-world benchmark applications w.r.t. branch coverage and real-fault detection capability. We also compare LT-MOSA with the two existing state-of-the-art white-box techniques (MIO, MOSA) for REST API testing. Our results show that LT-MOSA achieves a statistically significant increase in test target coverage (i.e., lines and branches) compared to MIO and MOSA in 4 and 5 out of 7 applications, respectively. Furthermore, LT-MOSA discovers 27 and 18 unique real-faults that are left undetected by MIO and MOSA, respectively.
The Android mining sandbox approach consists in running dynamic analysis tools on a benign version of an Android app and recording every call to sensitive APIs. Later, one can use this information to (a) prevent calls to other sensitive APIs (those n
ot previously recorded) or (b) run the dynamic analysis tools again in a different version of the app -- in order to identify possible malicious behavior. Although the use of dynamic analysis for mining Android sandboxes has been empirically investigated before, little is known about the potential benefits of combining static analysis with the mining sandbox approach for identifying malicious behavior. As such, in this paper we present the results of two empirical studies: The first is a non-exact replication of a previous research work from Bao et al., which compares the performance of test case generation tools for mining Android sandboxes. The second is a new experiment to investigate the implications of using taint analysis algorithms to complement the mining sandbox approach in the task to identify malicious behavior. Our study brings several findings. For instance, the first study reveals that a static analysis component of DroidFax (a tool used for instrumenting Android apps in the Bao et al. study) contributes substantially to the performance of the dynamic analysis tools explored in the previous work. The results of the second study show that taint analysis is also practical to complement the mining sandboxes approach, improve the performance of the later strategy in at most 28.57%.
