A Systematic Review of AI-Enabled Frameworks in Requirements Elicitation
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".