Getting Inspiration for Feature Elicitation: App Store- vs. LLM-based Approach

• Published in: IEEE/ACM International Conference on Automated Software Engineering : [proceedings] pp. 857 - 869
• Main Authors: Wei, Jialiang, Courbis, Anne-Lise, Lambolais, Thomas, Xu, Binbin, Bernard, Pierre Louis, Dray, Gerard, Maalej, Walid
• Format: Conference Proceeding
• Language: English
• Published: ACM 27.10.2024
• Subjects: App Store Mining; Creativity in SE; Data-Centered Requirements Engineering; Generative AI; Industries; Large language models; Manuals; Natural language processing; Refining; Requirements Elicitation; Reviews; Software; Software engineering; Surveys
• ISSN: 2643-1572
• DOI: 10.1145/3691620.3695591

Over the past decade, app store (AppStore)-inspired requirements elicitation has proven to be highly beneficial. Developers often explore competitors' apps to gather inspiration for new features. With the advance of Generative AI, recent studies have demonstrated the potential of large language model (LLM)-inspired requirements elicitation. LLMs can assist in this process by providing inspiration for new feature ideas. While both approaches are gaining popularity in practice, there is a lack of insight into their differences. We report on a comparative study between AppStore- and LLM-based approaches for refining features into sub-features. By manually analyzing 1,200 sub-features recommended from both approaches, we identified their benefits, challenges, and key differences. While both approaches recommend highly relevant sub-features with clear descriptions, LLMs seem more powerful particularly concerning novel unseen app scopes. Moreover, some recommended features are imaginary with unclear feasibility, which suggests the importance of a human-analyst in the elicitation loop.CCS CONCEPTS* Software and its engineering → Requirements analysis; * Computing methodologies → Natural language processing.