Pattern Learning for Detecting Defect Reports and Improvement Requests in App Reviews
This work addresses the need for automated classification of app reviews to reduce manual labor for developers and companies, though it is incremental as it builds on existing pattern learning and distant supervision methods.
The study tackled the problem of extracting actionable insights from app reviews by classifying them as defect reports or improvement requests, showing that automatically learned patterns outperformed manually created ones and that distantly-supervised SVM models performed competitively with limited annotated data.
Online reviews are an important source of feedback for understanding customers. In this study, we follow novel approaches that target this absence of actionable insights by classifying reviews as defect reports and requests for improvement. Unlike traditional classification methods based on expert rules, we reduce the manual labour by employing a supervised system that is capable of learning lexico-semantic patterns through genetic programming. Additionally, we experiment with a distantly-supervised SVM that makes use of noisy labels generated by patterns. Using a real-world dataset of app reviews, we show that the automatically learned patterns outperform the manually created ones, to be generated. Also the distantly-supervised SVM models are not far behind the pattern-based solutions, showing the usefulness of this approach when the amount of annotated data is limited.