The application of artificial intelligence in software engineering: a review challenging conventional wisdom

Batarseh, Feras A.; Mohod, Rasika; Kumar, Abhinav; Bui, Justin C.

doi:10.48550/arxiv.2108.01591

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI's role in SE spans from code completion to defect detection [1]. However, existing studies often focus on specific AI techniques or SE phases, with challenges in AI's integration into SE still prevalent [2,3]. The emergence of Explainable AI (XAI) in SE highlights the need for transparency in AI models [1].…”

Section: Ai and Software Engineeringmentioning

confidence: 99%

Gunning Fog Index and Automated UML Generation

Djaber,

HADJADJ

2023

Preprint

View full text Add to dashboard Cite

This research investigates the influence of the Gunning Fog Index (GFI) on the production of PlantUML use case diagrams by ChatGPT, within the context of software development projects, particularly focusing on E-commerce for Special Shoes. The study emphasizes the impact of linguistic complexity, as measured by GFI, on the automated code-generation process. It reveals that lower GFI scores, indicative of clearer text, lead to more easily comprehensible code representations, while higher scores correlate with intricate but potentially less accessible code artifacts. This reflects a nuanced balance between detail and clarity in the specifications. A key finding is the significant contribution of integrating linguistic clarity met-rics like GFI into the code generation workflow. This integration is shown to enhance code quality, usability, and facilitate collaboration among stakeholders. Despite the study’s focus on GFI to the exclusion of other readability metrics, it provides valuable insights into the role of linguistic complexity in shaping software artifacts generated by ChatGPT. Recognizing the importance of readability allows developers to more effectively translate natural language specifications into machine-generated code, yielding benefits in diverse project scenarios.

show abstract

Section: Ai and Software Engineeringmentioning

confidence: 99%

Gunning Fog Index and Automated UML Generation

Djaber,

HADJADJ

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The software engineering landscape is transforming with the integration of artificial intelligence [1][2][3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Class Diagram Dynamics: A Natural Language Approach with ChatGPT

Djaber

2024

Preprint

View full text Add to dashboard Cite

The present research introduces an innovative methodology, assisted by artificial intelligence, aimed at enhancing the dynamics of class diagrams within the field of software engineering. This methodology employs advanced language models, such as ChatGPT, to address the limitations inherent in traditional manual methods, particularly when dealing with complex systems. The approach is iterative, analyzing natural language use cases in detail and extracting key insights through the language understanding capabilities of ChatGPT. These insights are then integrated into a UML class diagram, resulting in demonstrable improvements in both accuracy and completeness. The updated diagram, supplemented with explicit methods derived from use cases, offers a more precise delineation of functional responsibilities and improved class relationships. This leads to a more comprehensive understanding of system interactions. This methodology, which is both versatile and efficient, aligns with UML best practices and holds significant value for Agile development. While further evaluation is necessary, preliminary findings suggest that AI-driven approaches hold considerable potential for enhancing the dynamics of class diagrams and advancing software development practices.

show abstract