一句话：对比 App Store 与 LLM 两种特性引出方法，发现 LLM 在新颖应用范围上更强，但推荐可行性与人类把关仍关键。
开发者常浏览竞品应用获取新特性灵感，基于应用商店（App Store）的特性引出已有价值；生成式 AI 兴起后，基于大语言模型（LLM）的方法也显现潜力，但二者差异缺乏系统认识。本文对 App Store 与 LLM 两种方法在将特性细化为子特性上进行对比，人工分析两者共推荐的 1,200 个子特性，归纳收益、挑战与关键差异。结果显示，两者都能给出高度相关、描述清晰的子特性；LLM 在未见过的应用范围上尤其更强，可提供新颖灵感。但部分推荐特性是想象性的，可行性不明，表明特性引出回路仍需人类分析师参与。
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.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{WeiCL0BDM24,
title = {Getting Inspiration for Feature Elicitation: App Store- vs. LLM-based Approach},
author = {Jialiang Wei and Anne-Lise Courbis and Thomas Lambolais and Binbin Xu and Pierre Louis Bernard and Gerard Dray and Walid Maalej},
booktitle = {ASE},
year = {2024},
doi = {10.1145/3691620.3695591}
}