Empirical evaluation of automated code generation for mobile applications by AI tools

Santiago Aillon; Alejandro Garcia; Nicolas Velandia; Daniel Zarate; Pedro Wightman

doi:10.1109/C358072.2023.10436306

Empirical evaluation of automated code generation for mobile applications by AI tools

Santiago Aillon
, Alejandro Garcia
, Nicolas Velandia
, Daniel Zarate
, Pedro Wightman

Research output: Chapter in Book/Inform › Conference contribution

5 Scopus citations

Abstract

The rapid advancement of AI technologies has opened up new possibilities for automating various aspects of software development. Mobile app development, in particular, can benefit from AI-powered tools that assist developers in writing code more efficiently, providing suggestions, and reducing the time required for implementation. This document aims to explore how well a modern artificial intelligence tool can assist a mobile application development process. For this work, ChatGPT 3.5 was used to generate a mobile application from scratch using the Flutter framework, while the complete process was evaluated at each step. The evaluation criteria for the experience considered four indicators: code quality, solution quality, response time, and comparison with human-generated code. Results show that, up to a certain level of complexity and by using an interactive process of increasingly detailed prompts, the AI tool is capable of generating functional code, that can be the base for the inclusion of a more complex logic or structure.

Original language	English (US)
Title of host publication	1st IEEE Colombian Caribbean Conference, C3 2023
Editors	Paul Sanmartin Mendoza, Andres Navarro
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350341799
DOIs	https://doi.org/10.1109/C358072.2023.10436306
State	Published - 2023
Event	1st IEEE Colombian Caribbean Conference, C3 2023 - Barranquilla, Colombia Duration: Nov 22 2023 → Nov 25 2023

Publication series

Name	1st IEEE Colombian Caribbean Conference, C3 2023

Conference

Conference	1st IEEE Colombian Caribbean Conference, C3 2023
Country/Territory	Colombia
City	Barranquilla
Period	11/22/23 → 11/25/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 1 No Poverty

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Electrical and Electronic Engineering
Mechanical Engineering
Control and Optimization
Modeling and Simulation
Instrumentation

Access to Document

10.1109/C358072.2023.10436306

Cite this

Aillon, S., Garcia, A., Velandia, N., Zarate, D., & Wightman, P. (2023). Empirical evaluation of automated code generation for mobile applications by AI tools. In P. S. Mendoza, & A. Navarro (Eds.), 1st IEEE Colombian Caribbean Conference, C3 2023 (1st IEEE Colombian Caribbean Conference, C3 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/C358072.2023.10436306

@inproceedings{9382af79988f46a6883eca2255b8574a,

title = "Empirical evaluation of automated code generation for mobile applications by AI tools",

abstract = "The rapid advancement of AI technologies has opened up new possibilities for automating various aspects of software development. Mobile app development, in particular, can benefit from AI-powered tools that assist developers in writing code more efficiently, providing suggestions, and reducing the time required for implementation. This document aims to explore how well a modern artificial intelligence tool can assist a mobile application development process. For this work, ChatGPT 3.5 was used to generate a mobile application from scratch using the Flutter framework, while the complete process was evaluated at each step. The evaluation criteria for the experience considered four indicators: code quality, solution quality, response time, and comparison with human-generated code. Results show that, up to a certain level of complexity and by using an interactive process of increasingly detailed prompts, the AI tool is capable of generating functional code, that can be the base for the inclusion of a more complex logic or structure.",

author = "Santiago Aillon and Alejandro Garcia and Nicolas Velandia and Daniel Zarate and Pedro Wightman",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 1st IEEE Colombian Caribbean Conference, C3 2023 ; Conference date: 22-11-2023 Through 25-11-2023",

year = "2023",

doi = "10.1109/C358072.2023.10436306",

language = "English (US)",

series = "1st IEEE Colombian Caribbean Conference, C3 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Mendoza, \{Paul Sanmartin\} and Andres Navarro",

booktitle = "1st IEEE Colombian Caribbean Conference, C3 2023",

address = "United States",

}

Aillon, S, Garcia, A, Velandia, N, Zarate, D & Wightman, P 2023, Empirical evaluation of automated code generation for mobile applications by AI tools. in PS Mendoza & A Navarro (eds), 1st IEEE Colombian Caribbean Conference, C3 2023. 1st IEEE Colombian Caribbean Conference, C3 2023, Institute of Electrical and Electronics Engineers Inc., 1st IEEE Colombian Caribbean Conference, C3 2023, Barranquilla, Colombia, 11/22/23. https://doi.org/10.1109/C358072.2023.10436306

Empirical evaluation of automated code generation for mobile applications by AI tools. / Aillon, Santiago; Garcia, Alejandro; Velandia, Nicolas et al.
1st IEEE Colombian Caribbean Conference, C3 2023. ed. / Paul Sanmartin Mendoza; Andres Navarro. Institute of Electrical and Electronics Engineers Inc., 2023. (1st IEEE Colombian Caribbean Conference, C3 2023).

Research output: Chapter in Book/Inform › Conference contribution

TY - GEN

T1 - Empirical evaluation of automated code generation for mobile applications by AI tools

AU - Aillon, Santiago

AU - Garcia, Alejandro

AU - Velandia, Nicolas

AU - Zarate, Daniel

AU - Wightman, Pedro

PY - 2023

Y1 - 2023

N2 - The rapid advancement of AI technologies has opened up new possibilities for automating various aspects of software development. Mobile app development, in particular, can benefit from AI-powered tools that assist developers in writing code more efficiently, providing suggestions, and reducing the time required for implementation. This document aims to explore how well a modern artificial intelligence tool can assist a mobile application development process. For this work, ChatGPT 3.5 was used to generate a mobile application from scratch using the Flutter framework, while the complete process was evaluated at each step. The evaluation criteria for the experience considered four indicators: code quality, solution quality, response time, and comparison with human-generated code. Results show that, up to a certain level of complexity and by using an interactive process of increasingly detailed prompts, the AI tool is capable of generating functional code, that can be the base for the inclusion of a more complex logic or structure.

AB - The rapid advancement of AI technologies has opened up new possibilities for automating various aspects of software development. Mobile app development, in particular, can benefit from AI-powered tools that assist developers in writing code more efficiently, providing suggestions, and reducing the time required for implementation. This document aims to explore how well a modern artificial intelligence tool can assist a mobile application development process. For this work, ChatGPT 3.5 was used to generate a mobile application from scratch using the Flutter framework, while the complete process was evaluated at each step. The evaluation criteria for the experience considered four indicators: code quality, solution quality, response time, and comparison with human-generated code. Results show that, up to a certain level of complexity and by using an interactive process of increasingly detailed prompts, the AI tool is capable of generating functional code, that can be the base for the inclusion of a more complex logic or structure.

UR - https://www.scopus.com/pages/publications/85186761633

UR - https://www.scopus.com/pages/publications/85186761633#tab=citedBy

U2 - 10.1109/C358072.2023.10436306

DO - 10.1109/C358072.2023.10436306

M3 - Conference contribution

AN - SCOPUS:85186761633

T3 - 1st IEEE Colombian Caribbean Conference, C3 2023

BT - 1st IEEE Colombian Caribbean Conference, C3 2023

A2 - Mendoza, Paul Sanmartin

A2 - Navarro, Andres

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st IEEE Colombian Caribbean Conference, C3 2023

Y2 - 22 November 2023 through 25 November 2023

ER -

Aillon S, Garcia A, Velandia N, Zarate D, Wightman P. Empirical evaluation of automated code generation for mobile applications by AI tools. In Mendoza PS, Navarro A, editors, 1st IEEE Colombian Caribbean Conference, C3 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (1st IEEE Colombian Caribbean Conference, C3 2023). doi: 10.1109/C358072.2023.10436306

Empirical evaluation of automated code generation for mobile applications by AI tools

Abstract

Publication series

Conference

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this