Ticket Tagger: Machine Learning Driven Issue Classification

Abstract

Software maintenance is crucial for software projects evolution and success: code should be kept up-to-date and error-free, this with little effort and continuous updates for the end-users. In this context, issue trackers are essential tools for creating, managing and addressing the several (often hundreds of) issues that occur in software systems. A critical aspect for handling and prioritizing issues involves the assignment of labels to them (e.g., for projects hosted on GitHub), in order to determine the type (e.g., bug report, feature request and so on) of each specific issue. Although this labeling process has a positive impact on the effectiveness of issue processing, the current labeling mechanism is scarcely used on GitHub. In this demo, we introduce a tool, called Ticket Tagger, which leverages machine learning strategies on issue titles and descriptions for automatically labeling GitHub issues. Ticket Tagger automatically predicts the labels to assign to issues, with the aim of stimulating the use of labeling mechanisms in software projects, this to facilitate the issue management and prioritization processes. Along with the presentation of the tool's architecture and usage, we also evaluate its effectiveness in performing the issue labeling/classification process, which is critical to help maintainers to keep control of their workloads by focusing on the most critical issue tickets.

BEE: a tool for structuring and analyzing bug reports

“…Based on the sentence-level classification, Bee determines if the bug report does not contain any of the three elements. [30], which is based on fast-Text [29]. The model is a multi-class linear neural model that receives the set of n-grams (i.e., sequences of n consecutive words) extracted from the issue title and description, and outputs the probability distribution of the issue over the predefined categories [30].…”

“…[30], which is based on fast-Text [29]. The model is a multi-class linear neural model that receives the set of n-grams (i.e., sequences of n consecutive words) extracted from the issue title and description, and outputs the probability distribution of the issue over the predefined categories [30]. The model is pre-trained using 30k issues from 12k GitHub projects and classifies an issue into one of three categories: bug report, enhancement, or question.…”

“…These categories are among the default labels of GitHub Issues [4]. The model can detect bug reports, enhancements, and questions with more than 82%, 76%, and 78% precision/recall, respectively, as indicated by its evaluation [30].…”

“…Many approaches have been proposed to classify issues into bug reports, feature requests, enhancements, questions, and other categories [6,9,24,25,30,38,39,44]. These approaches typically implement machine learning models that use textual features for classification.…”

“…These approaches typically implement machine learning models that use textual features for classification. Bee uses Ticket Tacker's pre-trained model [30] to identify if a newly-submitted issue reports a bug.…”