User Story Automation in Software Engineering: Insights from the Literature

User stories are widely regarded as an effective method for articulating software requirements, especially within agile development. However, the brevity often encouraged in user stories can lead to a lack of detail, resulting in miscommunication and inefficiencies during development. A significant challenge is the manual extraction of user stories from unstructured text, which is labor-intensive and prone to errors. Automated extraction using Natural Language Processing (NLP) and Machine Learning offers a promising solution. These technologies can identify and extract user roles, actions, and benefits from unstructured text, reducing the reliance on manual intervention and ensuring consistent quality. We conducted a literature review spanning the past 20 years, from 2004 to 2024, on which we identified 77 relevant articles, with only 10 focusing on the extraction of user stories using NLP techniques. These studies emphasize the need for automation in user story extraction to improve the efficiency and accuracy of requirements gathering. The findings highlight a gap in current research regarding automated extraction methods and the importance of addressing this through advanced NLP techniques. Implementing such solutions can transform the handling of user stories, making the requirements elicitation process more efficient and less error-prone, ultimately contributing to the success of agile software development projects.