Towards a Data-Driven Requirements Engineering Approach: Automatic Analysis of User Reviews
This work addresses the challenge of extracting requirements from user reviews for software developers, but it is incremental as it applies an existing method to a new dataset in a specific domain.
The paper tackled the problem of automatically analyzing user reviews for requirements engineering by creating a multi-label classification dataset of 6000 French reviews from Health & Fitness apps and using CamemBERT, a state-of-the-art language model, to identify requests for new features, with results described as encouraging.
We are concerned by Data Driven Requirements Engineering, and in particular the consideration of user's reviews. These online reviews are a rich source of information for extracting new needs and improvement requests. In this work, we provide an automated analysis using CamemBERT, which is a state-of-the-art language model in French. We created a multi-label classification dataset of 6000 user reviews from three applications in the Health & Fitness field. The results are encouraging and suggest that it's possible to identify automatically the reviews concerning requests for new features. Dataset is available at: https://github.com/Jl-wei/APIA2022-French-user-reviews-classification-dataset.