| Title |
Enhancing Systematic Literature Reviews using LDA and ChatGPT: Case of Framework for Smart City Planning |
| ID_Doc |
38252 |
| Authors |
Masinde, M |
| Title |
Enhancing Systematic Literature Reviews using LDA and ChatGPT: Case of Framework for Smart City Planning |
| Year |
2024 |
| Published |
|
| DOI |
|
| Abstract |
Systematic literature review (SLR) plays a crucial role in ensuring the originality, significance, and quality of research. However, conducting SLR can be a challenging task that is prone to errors and subjectivity. To mitigate these issues, text mining and machine learning (ML) techniques have been adopted. These techniques have been shown to improve the efficiency and quality of SLR. In this paper, we employ Latent Dirichlet Allocation (LDA) and Chat Generative Pre-Trained Transformer (ChatGPT) to conduct a comprehensive SLR on developments within smart cities, using a 7-step methodology. Our results demonstrate that LDA and ML (ChatGPT, in this case) can enhance SLR, resulting in over 80% improvement in both the efficiency and quality of the review. Specifically, the results highlight the importance of a comprehensive framework for planning and managing sustainable smart city projects, including stakeholder-driven design of common applications and deployment of technologies to implement these applications. The interrelationships between these themes are crucial for achieving the vision of a smart city. This paper contributes twofold: (1) a 7-step SLR methodology that incorporates LDA and ChatGPT and (2) a comprehensive SLR on the smart city concept. |
| Author Keywords |
systematic literature review; text mining; machine learning; Latent Dirichlet Allocation (LDA); Chat Generative Pre-Trained Transformer (ChatGPT); smart cities; sustainability; inclusivity; governance; multi-disciplinary approach |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Conference Proceedings Citation Index - Science (CPCI-S) |
| EID |
WOS:001268588100083 |
| WoS Category |
Computer Science, Interdisciplinary Applications; Computer Science, Theory & Methods; Engineering, Multidisciplinary |
| Research Area |
Computer Science; Engineering |
| PDF |
|