[Paper Review] Investigating the use of ChatGPT for the scheduling of construction projects

Samuel A. Prieto, Eyob Mengiste+1 more|arXiv (Cornell University)|Jan 27, 2023

Artificial Intelligence in Healthcare and Education26 citations

TL;DR

The paper assesses ChatGPT’s ability to generate a coherent construction schedule for a simple project and evaluates user experience and output quality through participant feedback.

ABSTRACT

Large 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 great potential of such a tool to automate 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 potential of using large language models in the construction industry and the need for further research.

Motivation & Objective

• Motivate the use of large language models to automate repetitive scheduling tasks in construction.
• Investigate whether ChatGPT can generate a coherent construction schedule that fulfills project scope.
• Evaluate the user interaction experience and perceived output quality of ChatGPT-generated schedules.
• Identify limitations and areas for further development before wide industry adoption.

Proposed method

• Use ChatGPT to generate a construction schedule for a simple project.
• Assemble a pool of participants to evaluate the ChatGPT output.
• Collect feedback on interaction experience and schedule quality.
• Analyze whether the produced schedule follows a logical approach to the stated scope.
• Discuss potential applications and development needs based on findings.

Experimental results

Research questions

• RQ1 Can ChatGPT generate a coherent construction schedule that aligns with a given project scope?
• RQ2 What is the perceived quality and usability of ChatGPT-generated schedules from the perspective of users?
• RQ3 What limitations or challenges arise when using ChatGPT for construction scheduling, and what improvements are needed?

Key findings

• ChatGPT can produce a coherent schedule that follows a logical approach to satisfy the indicated scope.
• Participants reported an overall positive interaction experience with using ChatGPT for scheduling tasks.
• Participants see substantial potential for automating preliminary and time-consuming scheduling tasks in construction.
• The technology exhibits limitations and requires further development before broad industry adoption.