Scholarlink

<p>User Stories record what must be built in projects that use agile practices and serve both to estimate effort, generally measured in Story Points, and to plan what should be done in a Sprint. Therefore, it is essential to create simple, easily readable, and comprehensive User Stories. This article proposes a method to help agile teams create high-quality User Stories. The proposal uses natural language processing, large-scale language models, and machine learning to provide personalized recommendations to improve User Stories, estimate effort in Story Points, and evaluate text readability. The tool was evaluated with a questionnaire based on the Technology Acceptance Model and AttrakDiff frameworks and measured usability, ease of use, external factors, and participants’ attitudes toward the proof-of-concept. The proposal demonstrates the potential to improve user story creation, and the participants responded positively, describing it as both useful and easy to use. Furthermore, the data set used is also presented.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Writing Better User Stories and Estimates Story Point with Machine Learning and Natural Language Processing

  • 期刊论文

  • 发表日期：

    2025年9月12日

查看全文
  • Giseldo da Silva Neo,
  • José Antão Beltrão Moura,
  • Hyggo Oliveira de Almeida,
  • Alana Viana Borges da Silva Neo,
  • Olival de Gusmão Freitas Júnior

摘要

User Stories record what must be built in projects that use agile practices and serve both to estimate effort, generally measured in Story Points, and to plan what should be done in a Sprint. Therefore, it is essential to create simple, easily readable, and comprehensive User Stories. This article proposes a method to help agile teams create high-quality User Stories. The proposal uses natural language processing, large-scale language models, and machine learning to provide personalized recommendations to improve User Stories, estimate effort in Story Points, and evaluate text readability. The tool was evaluated with a questionnaire based on the Technology Acceptance Model and AttrakDiff frameworks and measured usability, ease of use, external factors, and participants’ attitudes toward the proof-of-concept. The proposal demonstrates the potential to improve user story creation, and the participants responded positively, describing it as both useful and easy to use. Furthermore, the data set used is also presented.