Investigating the Use of ChatGPT for the Scheduling of Construction Projects

Samuel A. Prieto; Eyob T. Mengiste; Borja García de Soto

doi:10.3390/buildings13040857

Investigating the Use of ChatGPT for the Scheduling of Construction Projects

Samuel A. Prieto, Eyob T. Mengiste, Borja García de Soto

Civil Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

Generative Pre-Trained Transformer (GPT) language models such as ChatGPT have the potential to revolutionize the construction industry by automating repetitive and time-consuming tasks. This paper presents a study in which ChatGPT was used to generate a construction schedule for a simple construction project. The output from ChatGPT was evaluated by a pool of participants that provided feedback regarding their overall interaction experience and the quality of the output. The results show that ChatGPT can generate a coherent schedule that follows a logical approach to fulfill the requirements of the scope indicated. The participants had an overall positive interaction experience and indicated the potential of such a tool in automating many preliminary and time-consuming tasks. However, the technology still has limitations, and further development is needed before it can be widely adopted in the industry. Overall, this study highlights the advantages of using large language models and Natural Language Processing (NLP) techniques in the construction industry and the need for further research.

Original language	English (US)
Article number	857
Journal	Buildings
Volume	13
Issue number	4
DOIs	https://doi.org/10.3390/buildings13040857
State	Published - Apr 2023

Keywords

ChatGPT
Construction 5.0
GPT 3.5
generative pre-training transformer
natural language processing
project management
scheduling

ASJC Scopus subject areas

Architecture
Civil and Structural Engineering
Building and Construction

Access to Document

10.3390/buildings13040857

Cite this

@article{18618223ebde432987a93fe655fea424,

title = "Investigating the Use of ChatGPT for the Scheduling of Construction Projects",

abstract = "Generative Pre-Trained Transformer (GPT) language models such as ChatGPT have the potential to revolutionize the construction industry by automating repetitive and time-consuming tasks. This paper presents a study in which ChatGPT was used to generate a construction schedule for a simple construction project. The output from ChatGPT was evaluated by a pool of participants that provided feedback regarding their overall interaction experience and the quality of the output. The results show that ChatGPT can generate a coherent schedule that follows a logical approach to fulfill the requirements of the scope indicated. The participants had an overall positive interaction experience and indicated the potential of such a tool in automating many preliminary and time-consuming tasks. However, the technology still has limitations, and further development is needed before it can be widely adopted in the industry. Overall, this study highlights the advantages of using large language models and Natural Language Processing (NLP) techniques in the construction industry and the need for further research.",

keywords = "ChatGPT, Construction 5.0, GPT 3.5, generative pre-training transformer, natural language processing, project management, scheduling",

author = "Prieto, {Samuel A.} and Mengiste, {Eyob T.} and {Garc{\'i}a de Soto}, Borja",

note = "Funding Information: The authors thank the participants who provided their feedback and experience using ChatGPT for the case study. This work was supported by the Center for Cyber Security (CCS) at New York University Abu Dhabi, funded by Tamkeen under the NYUAD Research Institute Award G1104 in collaboration with the NYUAD Center for Interacting Urban Networks (CITIES), funded by Tamkeen under the NYUAD Research Institute Award CG001. Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = apr,

doi = "10.3390/buildings13040857",

language = "English (US)",

volume = "13",

journal = "Buildings",

issn = "2075-5309",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "4",

}

TY - JOUR

T1 - Investigating the Use of ChatGPT for the Scheduling of Construction Projects

AU - Prieto, Samuel A.

AU - Mengiste, Eyob T.

AU - García de Soto, Borja

N1 - Funding Information: The authors thank the participants who provided their feedback and experience using ChatGPT for the case study. This work was supported by the Center for Cyber Security (CCS) at New York University Abu Dhabi, funded by Tamkeen under the NYUAD Research Institute Award G1104 in collaboration with the NYUAD Center for Interacting Urban Networks (CITIES), funded by Tamkeen under the NYUAD Research Institute Award CG001. Publisher Copyright: © 2023 by the authors.

PY - 2023/4

Y1 - 2023/4

N2 - Generative Pre-Trained Transformer (GPT) language models such as ChatGPT have the potential to revolutionize the construction industry by automating repetitive and time-consuming tasks. This paper presents a study in which ChatGPT was used to generate a construction schedule for a simple construction project. The output from ChatGPT was evaluated by a pool of participants that provided feedback regarding their overall interaction experience and the quality of the output. The results show that ChatGPT can generate a coherent schedule that follows a logical approach to fulfill the requirements of the scope indicated. The participants had an overall positive interaction experience and indicated the potential of such a tool in automating many preliminary and time-consuming tasks. However, the technology still has limitations, and further development is needed before it can be widely adopted in the industry. Overall, this study highlights the advantages of using large language models and Natural Language Processing (NLP) techniques in the construction industry and the need for further research.

AB - Generative Pre-Trained Transformer (GPT) language models such as ChatGPT have the potential to revolutionize the construction industry by automating repetitive and time-consuming tasks. This paper presents a study in which ChatGPT was used to generate a construction schedule for a simple construction project. The output from ChatGPT was evaluated by a pool of participants that provided feedback regarding their overall interaction experience and the quality of the output. The results show that ChatGPT can generate a coherent schedule that follows a logical approach to fulfill the requirements of the scope indicated. The participants had an overall positive interaction experience and indicated the potential of such a tool in automating many preliminary and time-consuming tasks. However, the technology still has limitations, and further development is needed before it can be widely adopted in the industry. Overall, this study highlights the advantages of using large language models and Natural Language Processing (NLP) techniques in the construction industry and the need for further research.

KW - ChatGPT

KW - Construction 5.0

KW - GPT 3.5

KW - generative pre-training transformer

KW - natural language processing

KW - project management

KW - scheduling

UR - http://www.scopus.com/inward/record.url?scp=85153604641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85153604641&partnerID=8YFLogxK

U2 - 10.3390/buildings13040857

DO - 10.3390/buildings13040857

M3 - Article

AN - SCOPUS:85153604641

SN - 2075-5309

VL - 13

JO - Buildings

JF - Buildings

IS - 4

M1 - 857

ER -

Investigating the Use of ChatGPT for the Scheduling of Construction Projects

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this