Multidomain Drivers of Occupant Comfort, Productivity, and Well-Being in Buildings: Insights from an Exploratory and Explanatory Analysis
Bibliographic record
Abstract
Effective building management strategies require a clear understanding of how occupants perceive their indoor environmental conditions. Despite their important findings, previous studies were mostly limited to single-domain evaluations of the indoor environment (e.g., thermal, visual, acoustic, or air quality), and rarely considered general well-being or productivity metrics. A holistic data analysis approach is proposed to quantify the multidomain drivers of overall comfort, perceived productivity, and perceived happiness of occupants. The approach combines exploratory and explanatory analysis methods (correlation, correspondence analysis, and machine learning) and was demonstrated using data collected from 206 occupants of 3 buildings in Abu Dhabi, United Arab Emirates. Results showed that satisfaction levels with noise, air quality, and temperature are the main drivers of the studied multidomain metrics. However, threshold-based relationships were observed at the comfort scale’s extremes, challenging the linearity assumption often adopted in previous studies. Practical implications of the findings include focusing facility management efforts on specific environmental domains that act as levers for overall satisfaction and well-being, instead of aiming to improve satisfaction with all domains simultaneously. Such levers are context-dependent, confirming the need for the proposed data analysis approach that is applicable to any built environment. Finally, the case study also highlighted the modeling capabilities of the tested machine learning algorithms (support vector machine, random forest, and gradient boosting), which achieved predictive accuracies up to 38% higher than those of regression-based statistical models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".