Identifying non-natural language artifacts in bug reports

TL;DR

This paper introduces a machine learning method to automatically identify and filter out non-natural language artifacts like code snippets and logs in bug reports, improving NLP analysis accuracy.

Contribution

It presents a novel Python-based classifier trained on GitHub data that effectively distinguishes natural language from artifacts in bug reports.

Findings

Achieved 0.95 ROC-AUC and 0.93 F1 scores on validation

Classifies 10,000 lines in under a second

Model generalizes well across datasets

Abstract

Bug reports are a popular target for natural language processing (NLP). However, bug reports often contain artifacts such as code snippets, log outputs and stack traces. These artifacts not only inflate the bug reports with noise, but often constitute a real problem for the NLP approach at hand and have to be removed. In this paper, we present a machine learning based approach to classify content into natural language and artifacts at line level implemented in Python. We show how data from GitHub issue trackers can be used for automated training set generation, and present a custom preprocessing approach for bug reports. Our model scores at 0.95 ROC-AUC and 0.93 F1 against our manually annotated validation set, and classifies 10k lines in 0.72 seconds. We cross evaluated our model against a foreign dataset and a foreign R model for the same task. The Python implementation of our model and our datasets are made publicly available under an open source license.