arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.17404cs.SEcs.AI
收藏

为特征启发获取灵感:应用商店驱动的方法 vs. LLM驱动的方法

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

EuroMov Digital Health in Motion(EuroMov数字健康运动中心);Univ Montpellier(蒙彼利埃大学);IMT Mines Ales(阿尔比-加工程师学院);University of Hamburg(汉堡大学)

Jialiang Wei, Anne-Lise Courbis, Thomas Lambolais, Binbin Xu, Pierre Louis Bernard, Gérard Dray, Walid Maalej

AI总结:

本文对比了基于AppStore和LLM的需求启发方法在将特征细化为子特征方面的表现,发现LLM在生成新颖特征上更具优势,但仍需人类分析师确保可行性。

摘要:

过去十年中,受应用商店启发的需求启发已被证明非常有益。开发者经常探索竞争对手的应用程序,以收集新特征的灵感。随着生成式AI的进步,最近的研究证明了受大语言模型(LLM)启发的需求启发的潜力。LLMs可以通过为新特征想法提供灵感来协助此过程。虽然这两种方法在实践中都越来越受欢迎,但缺乏对其差异的深入了解。我们报告了一项比较研究,比较了基于AppStore和基于LLM的方法,用于将特征细化为子特征。通过手动分析这两种方法推荐的1,200个子特征,我们确定了它们的优势、挑战和关键差异。虽然两种方法都推荐了具有清晰描述的高度相关的子特征,但LLMs似乎更强大,特别是在新颖的未见应用范围方面。此外,一些推荐的特征是虚构的,可行性不明确,这表明人类分析师在启发循环中的重要性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑