Measuring building information modeling user satisfaction by using active interpretable machine learning

doi:10.1016/j.asoc.2025.113663

Measuring building information modeling user satisfaction by using active interpretable machine learning

2025-07-25

0

PRE

AI

DOI：10.1016/j.asoc.2025.113663

Original

Original request for help

Save

Abstract

En 中文

• Developed an active interpretable machine learner to measure BIM user satisfaction (US). • Proved the practical efficiency of the proposed model for 70 BIM projects in Taiwan. • Achieved the highest accuracy and F1 scores up to 88.6 % and 87.8 %, respectively. • Identified base analysis, project scale, and cost estimates as crucial for improving BIM US.

Keywords:

BIM user satisfaction

interpretable machine learning

model accuracy

F1 score

project factors

Measuring building information modeling user satisfaction by using active interpretable machine learning

Abstract

Journal

Organization

Cited Papers