Augmenting GitHub Issues with Apple App Store Reviews: A Replication Study

Publication Date

Spring 4-22-2026

Presentation Length

15 minutes

College

College of Sciences & Mathematics

Department

Math and Computer Science, Department of

Student Level

Undergraduate

Faculty Mentor

Dr Esteban Parra Rodriguez

Presentation Type

Talk/Oral

Summary

User reviews on app stores contain valuable information for developers regarding bugs and missing features, but it’s hard for developers to have time to read every single one as there can be thousands of them. Previous work proposed an automated approach that helps to bridge this gap by linking reviews from the Google Play Store to relevant GitHub issues using semantic similarity. By converting both reviews and issues into numerical representations and finding the closest matches, the process of receiving feedback can be expedited. This study replicates and extends this idea, using the Apple App Store instead of Google Play reviews and testing if the semantic similarity approach works across platforms. I collect App Store reviews for a set of open-source mobile applications, that also have public GitHub repositories, using the same embedding model and pipeline as the original study, as well as compute similarity scores between reviews and issues and evaluate the quality of the resulting matches through manual annotation.

This document is currently not available here.

Share

COinS