Machine Learning in Requirements Engineering: A Mapping Study
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the IEEE International Conference on Requirements Engineering, 2021, 2021-September, pp. 116-125
- Issue Date:
- 2021-09-01
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Machine_Learning_in_Requirements_Engineering_A_Mapping_Study.pdf | Published version | 366.17 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Machine learning (ML) techniques are used to make the software development process more efficient and effective. Many ML approaches have also been proposed to automate Requirements Engineering (RE) activities such as ambiguity detection, traceability analysis and to address complex RE challenges. The overall goal of this research is to explore the state of the art of application of ML in RE and to determine the effectiveness of ML in improving the RE process and artefacts. Following the Evidence-Based Software Engineering approach, we performed a mapping study of the empirical studies on ML techniques and approaches used in RE published between 2010 and April 2020. Data were extracted from the selected papers about the ML techniques, problems, and challenges of using ML, identification of the used datasets, and the evaluation metrics employed to assess the ML techniques. We analyzed 65 relevant papers in this mapping study. Our analysis shows that ML is an effective tool for automating RE analysis tasks, overcoming complexity, and reducing cost and time. We also present the gaps in the ML for RE literature and suggest areas that need further research.
Please use this identifier to cite or link to this item: