Developers frequently discuss aspects of the systems they are developing online. The comments they post to discussions form a rich information source about the system. Intention mining, a process introduced by Di Sorbo et al., classifies sentences in developer discussions to enable further analysis. As one example of use, intention mining has been used to help build various recommenders for software developers. The technique introduced by Di Sorbo et al. to categorize sentences is based on linguistic patterns derived from two projects. The limited number of data sources used in this earlier work introduces questions about the comprehensiveness of intention categories and whether the linguistic patterns used to identify the categories are generalizable to developer discussion recorded in other kinds of software artifacts (e.g., issue reports). To assess the comprehensiveness of the previously identified intention categories and the generalizability of the linguistic patterns for category identification, we manually created a new dataset, categorizing 5,408 sentences from issue reports of four projects in GitHub. Based on this manual effort, we refined the previous categories. We assess Di Sorbo et al.'s patterns on this dataset, finding that the accuracy rate achieved is low (0.31). To address the deficiencies of Di Sorbo et al.'s patterns, we propose and investigate a convolution neural network (CNN)-based approach to automatically classify sentences into different categories of intentions. Our approach optimizes CNN by integrating batch normalization to accelerate the training speed, and an automatic hyperparameter tuning approach to tune appropriate hyperparameters of CNN. Our approach achieves an accuracy of 0.84 on the new dataset, improving Di Sorbo et al.'s approach by 171 percent. We also apply our approach to improve an automated software engineering task, in which we use our proposed approach to rectify misclassified issue reports, thus reducing the bias introduced by such data to other studies. A case study on four open source projects with 2,076 issue reports shows that our approach achieves an average AUC score of 0.687, which improves other baselines by at least 16 percent.

中文翻译：

---

自动化意图挖掘

开发人员经常在线讨论他们正在开发的系统的各个方面。他们在讨论中发表的评论构成了有关系统的丰富信息源。意图挖掘是 Di Sorbo 等人引入的一个过程，它对开发人员讨论中的句子进行分类，以便进行进一步的分析。作为一个使用示例，意图挖掘已被用于帮助为软件开发人员构建各种推荐系统。Di Sorbo 等人介绍的技术。对句子进行分类是基于源自两个项目的语言模式。早期工作中使用的有限数量的数据源引入了关于意图类别的全面性以及用于识别类别的语言模式是否可推广到记录在其他类型的软件工件（例如，问题报告）中的开发人员讨论的问题。为了评估先前识别的意图类别的全面性和类别识别语言模式的普遍性，我们手动创建了一个新数据集，对来自 GitHub 中四个项目的问题报告的 5,408 个句子进行分类。基于此手动工作，我们改进了之前的类别。我们在这个数据集上评估 Di Sorbo 等人的模式，发现达到的准确率很低 (0.31)。为了解决 Di Sorbo 等人模式的缺陷，我们提出并研究了一种基于卷积神经网络 (CNN) 的方法，以将句子自动分类为不同类别的意图。我们的方法通过集成批量归一化来加速训练速度来优化 CNN，并通过自动超参数调整方法来调整 CNN 的适当超参数。我们的方法在新数据集上实现了 0.84 的准确率，将 Di Sorbo 等人的方法提高了 171%。我们还应用我们的方法来改进自动化软件工程任务，其中我们使用我们提出的方法来纠正错误分类的问题报告，从而减少此类数据引入其他研究的偏差。对包含 2,076 份问题报告的四个开源项目的案例研究表明，我们的方法实现了 0.687 的平均 AUC 分数，这将其他基线提高了至少 16%。从而减少此类数据引入其他研究的偏差。对包含 2,076 份问题报告的四个开源项目的案例研究表明，我们的方法实现了 0.687 的平均 AUC 分数，这将其他基线提高了至少 16%。从而减少这些数据引入其他研究的偏差。对包含 2,076 份问题报告的四个开源项目的案例研究表明，我们的方法实现了 0.687 的平均 AUC 分数，这将其他基线提高了至少 16%。