Evaluation of Satisfaction with the Built Environment of University Buildings under the Epidemic and Its Impact on Student Anxiety.

Anxiety on college campuses has increased due to the COVID-19 epidemic's profound effects on society. Much research has been conducted on how the built environment influences mental health; however, little has been undertaken on how it affects student mental health in the context of the epidemic from the architectural scale perspective of academic buildings. Based on online survey data, this study develops multiple linear regression and binary logistic regression models to investigate students' satisfaction ratings of the academic buildings' physical environments during the epidemic and how these satisfaction ratings affect students' anxiety tendencies. According to the study's findings regarding the natural exposure perspective, students who perceived the academic building's poor semi-open space view (p = 0.004, OR = 3.22) as unsatisfactory factors were more likely to show anxiety tendencies. In terms of the physical conditions, students who were dissatisfied with the noise level in the classroom (p = 0.038, OR = 0.616) and the summer heat in semi-open spaces (p = 0.031, OR = 2.38) were more likely to exhibit anxiety tendencies. Additionally, even after controlling for confusing distractions, the general satisfaction rating of the academic building's physical environments (p = 0.047, OR = 0.572) was still able to significantly and negatively affect students' anxiety tendencies. The study's findings can be used in the architectural and environmental planning of academic buildings focusing on mental health.

Supervised learning-based assessment of office layout satisfaction in academic buildings

Employee satisfaction significantly affects health, well-being and productivity, and office layout plays a dominant role in office psychological satisfaction. However, existing studies have not yet proposed a quantitative evaluation method for office layout satisfaction to assist design decisions. This study conducts a post-occupancy evaluation (POE) process of office layout satisfaction from 1,317 staff members at 3 universities in the Yangtze River Delta, China. The proposed office layout feature network supports the questionnaire design and environmental measurement. Based on the survey data, multiple resampling methods are considered to face the imbalanced dataset problem, and feature selection integrates statistical analysis methods and machine learning algorithms. Nine supervised learning algorithms are tested for office layout satisfaction prediction, and the final predictive model is established based on the random forest algorithm. The predictive model explanation is further integrated with original data analysis to extract the quantified impacts of various building characteristics. The workstation adjustment under the background of COVID-19 in an actual staff office is chosen to be an application scenario of the predictive model. The results show that the workstation distance, room depth and room width-depth ratio are dominant in the evaluation of office layout satisfaction. The proposed predictive model achieves 64.5% accuracy, and the prediction results are interpretable, which promotes its application in office design practice. The data processing methods in this study respond to the common data problems in the POE based opinion collection process. The extracted influence mechanisms of building characteristics can directly support user-centered office design.