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

TL;DR

This study compares app store-inspired and LLM-based feature elicitation methods, analyzing 1,200 sub-features to understand their benefits, challenges, and differences, highlighting LLMs' potential and limitations.

Contribution

It provides a comparative analysis of AppStore- and LLM-based feature elicitation approaches, revealing their respective strengths, weaknesses, and the importance of human oversight.

Findings

Both approaches recommend relevant sub-features with clear descriptions.

LLMs are more effective for novel, unseen app scopes.

Some LLM-generated features are imaginary and lack feasibility.

Abstract

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.