Developers often reuse code fragments by copy-and-paste activities to speed up code delivery. Through this copy-and-paste process, they create duplicated code, also known as code clones. As the software system evolves, the number of clones can increase substantially and impact code quality negatively. Prior studies have shown that inconsistent changes on code clones can introduce bugs in a software system and clones that have experienced some specific evolutionary patterns being more at risk than others. As the number of clone copies increases in a software system. it becomes tedious and time-consuming for developers to track and maintain all code clones. Recent studies have proposed approaches to analyze the clone evolution history for better clone maintenance. However, these approaches do not provide a specified list of code clones at a granular level (i.e., commits) that can help developers prioritize their clone maintenance activities. It is important to track the code clone changes at the commit level, as developers can fix/refactor code clones early. In this paper, we leverage machine learning to develop clone ranking models that can help developers identify the most risky clones early on. Specifically, we detect clones from 52 projects (34 Java and 18 C) that have 534,672 commits and build 469,239 clone genealogies. We extract 28 features capturing the characteristics of code clones at commit level. We then train learning-to-rank (LtR), classification, and regression machine learning models to rank the code clones based on fault occurrence during their evolutionary history. Our comparison of machine learning approaches indicates that classification (for the probability of being faulty) and regression (for the proportion of faulty changes) perform well in ranking code clones. Multiple unique developers who change a code clone and the age of a code clone (in terms of the number of cloned code changes) have a significant effect on the risk of faults in the code clones. Our results can help developers identify the most risky code clones first and prioritize them for refactoring to prevent future faults.

Developer chatrooms (e.g., the Gitter platform) are gaining popularity as a communication channel among developers. In developer chatrooms, a developer ( asker ) posts questions and other developers ( respondents ) respond to the posted questions. The interaction between askers and respondents results in a discussion thread . Recent studies show that developers use chatrooms to inquire about issues, discuss development ideas, and help each other. However, prior work focuses mainly on analyzing individual messages of a chatroom without analyzing the discussion thread in a chatroom. Developer chatroom discussions are context-sensitive, entangled, and include multiple participants that make it hard to accurately identify threads. Therefore, prior work has limited capability to show the interactions among developers within a chatroom by analyzing only individual messages. In this article, we perform an in-depth analysis of the Gitter platform (i.e., developer chatrooms) by analyzing 6,605,248 messages of 709 chatrooms. To analyze the characteristics of the posted questions and the impact on the response behavior (e.g., whether the posted questions get responses), we propose an approach that identifies discussion threads in chatrooms with high precision (i.e., 0.81 F-score). Our results show that inactive members responded more often and unique questions take longer discussion time than simple questions. We also find that clear and concise questions are more likely to be responded to than poorly written questions. We further manually analyze a randomly selected sample of 384 threads to examine how respondents resolve the raised questions. We observe that more than 80% of the studied threads are resolved. Advanced-level/beginner-level questions along with the edited questions are the mostly resolved questions. Our results can help the project maintainers understand the nature of the discussion threads (e.g., the topic trends). Project maintainers can also benefit from our thread identification approach to spot the common repeated threads and use these threads as frequently asked questions (FAQs) to improve the documentation of their projects.