IEEE Access (Jan 2024)

A Systematic Review of AI-Enabled Frameworks in Requirements Elicitation

  • Vaishali Siddeshwar,
  • Sanaa Alwidian,
  • Masoud Makrehchi

DOI
https://doi.org/10.1109/ACCESS.2024.3475293
Journal volume & issue
Vol. 12
pp. 154310 – 154336

Abstract

Read online

Employing Artificial Intelligence techniques to address challenges in requirements elicitation is gaining traction. Although nine systematic literature reviews have been published on AI-based solutions in the requirements elicitation domain, to our knowledge, these studies do not cover a broad spectrum of elicitation tasks, data sources used for training, the performance of these algorithms, nor do they pinpoint the strengths and limitations of the algorithms used. This study contributes to the field by presenting a systematic literature review that explores the use of machine learning and NLP techniques in the elicitation phase of requirements engineering. The following research questions are addressed: 1) What elicitation tasks are supported by AI and what AI algorithms were employed? 2) What data sources have been used to construct AI-based solutions? 3) What performance outcomes were achieved? 4) What are the strengths and limitations of the current AI methods? Initially, 665 papers were retrieved from six data sources, and ultimately, 122 articles were selected for the review. This literature review identifies fifteen elicitation tasks currently supported by artificial intelligence and presents twelve publicly available data sources used for training these approaches. Furthermore, the study uncovers common limitations in current studies and suggests potential research directions. Overall, this systematic literature review provides insights into future research prospects for applying AI techniques to problems in the requirements elicitation domain.

Keywords