LinkFormer: Automatic Contextualised Link Recovery of Software Artifacts in both Project-based and Transfer Learning Settings

Software artifacts often interact with each other throughout the software development cycle. Associating related artifacts is a common practice for effective documentation and maintenance of software projects. Conventionally, to register the link between an issue report and its associated commit, developers manually include the issue identifier in the message of the relevant commit. Research has shown that developers tend to forget to connect said artifacts manually, resulting in a loss of links. Hence, several link recovery techniques were proposed to discover and revive such links automatically. However, the literature mainly focuses on improving the prediction accuracy on a randomly-split test set, while neglecting other important aspects of this problem, including the effect of time and generalizability of the predictive models. In this paper, we propose LinkFormer to address this problem from three aspects; 1) Accuracy: To better utilize contextual information for prediction, we employ the Transformer architecture and fine-tune multiple pre-trained models on textual and metadata of issues and commits. 2) Data leakage: To empirically assess the impact of time through the splitting policy, we train and test our proposed model along with several existing approaches on both randomly- and temporally split data. 3) Generalizability: To provide a generic model that can perform well across different projects, we further fine-tune LinkFormer in two transfer learning settings. We empirically show that researchers should preserve the temporal flow of data when training learning-based models to resemble the real-world setting. In addition, LinkFormer significantly outperforms the state-of-the-art by large margins. LinkFormer is also capable of extending the knowledge it learned to unseen projects with little to no historical data.

A ground-truth dataset and classification model for detecting bots in GitHub issue and PR comments

Bots are frequently used in Github repositories to automate repetitive activities that are part of the distributed software development process. They communicate with human actors through comments. While detecting their presence is important for many reasons, no large and representative ground-truth dataset is available, nor are classification models to detect and validate bots on the basis of such a dataset. This paper proposes such a ground-truth dataset, based on a manual analysis with high interrater agreement, of pull request and issue comments in 5,000 distinct Github accounts of which 527 accounts have been identified as bots. Using this dataset we propose an automated classification model based on the random forest classifier, taking as main features the number of empty and non-empty comments of each account, the number of comment patterns, and the inequality between comments within comment patterns. We obtained a very high accuracy (weighted F1-score of 0.99) on the remaining test set containing 40% of the data. Only 8 out of 211 bots in the test set are misclassified as humans. We integrated the classification model into an open source command-line tool, to allow practitioners to detect which accounts in a given Github repository actually correspond to bots.