What did the occupant say? Fine-tuning and evaluating a large language model for efficient analysis of multi-domain indoor environmental quality feedback

被引：0

作者：

Sadick, Abdul-Manan ^{[1
]}

Chinazzo, Giorgia ^{[2
]}

机构：

[1] Deakin Univ, Fac Sci Engn & Built Environm, Sch Architecture & Built Environm, Geelong Waterfront, Geelong, Australia

[2] Northwestern Univ, Dept Civil & Environm Engn, Evanston, IL 60208 USA

来源：

BUILDING AND ENVIRONMENT | 2025年 / 274卷

关键词：

Indoor environmental quality; Occupant feedback; Multi-domain; Natural language processing; Artificial intelligence; HEALTH;

D O I：

10.1016/j.buildenv.2025.112735

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

Qualitative feedback from occupants on indoor environmental quality (IEQ) in unstructured text can provide valuable insights into the causes of comfort and discomfort in buildings. This feedback can be collected from open-ended survey questions, interviews, crowdsourced data, or innovative home automation technology that can transform voice inputs into text. However, manual text data processing is time-consuming and requires significant efforts to extract relevant insights, such as text classification into IEQ categories (i.e., visual, thermal, air quality and acoustic). Most IEQ studies that automated text feedback classification into IEQ categories relied on keyword matching, which cannot understand the context of some keywords, potentially leading to incorrect classification. To address this issue, we automated the detection and categorisation of unstructured IEQ feedback by adopting the Bidirectional Encoder Representations from Transformers (BERT) language model architecture and fine-tuning it on 14,622 manually labelled IEQ text feedback. The resulting model, IEQ-BERT, achieved a prediction accuracy of 93 % and macro average precision, recall, and F1-scores of 0.93, 0.94, and 0.93, respectively, across the five considered classes (i.e., acoustic, indoor air quality, thermal, visual, or No IEQ). Therefore, the model can effectively distinguish text concerning IEQ and identify which IEQ domain - acoustic, indoor air quality, thermal, visual, or their combinations - is being reported. IEQ-BERT can be used alone or integrated into building automation systems to identify patterns and trends of occupant feedback, prioritise areas for improvement, and support the development of targeted strategies to improve IEQ. This research contributes to developing efficient methods for analysing occupant feedback, ultimately leading to improved building performance and occupant quality of life.

引用

页数：20

共 65 条

[1]

Kelly F.J., Fussell J.C., Improving indoor air quality, health and performance within environments where people live, travel, learn and work, Atmos. Environ., 200, pp. 90-109, (2019)

[2]

Zhao D., Azimi P., Stephens B., Evaluating the long-term health and economic impacts of central residential air filtration for reducing premature mortality associated with indoor fine particulate matter (PM2. 5) of outdoor origin, Int. J. Environ. Res. Public Health, 12, 7, pp. 8448-8479, (2015)

[3]

Shum C., Zhong L., Wildfire-resilient mechanical ventilation systems for single-detached homes in cities of Western Canada, Sustain. Cities Soc., 79, (2022)

[4]

Kallio J., Vildjiounaite E., Koivusaari J., Rasanen P., Simila H., Kyllonen V., Muuraiskangas S., Ronkainen J., Rehu J., Vehmas K., Assessment of perceived indoor environmental quality, stress and productivity based on environmental sensor data and personality categorization, Build. Environ., 175, (2020)

[5]

Demanega I., Mujan I., Singer B.C., Andelkovic A.S., Babich F., Licina D., Performance assessment of low-cost environmental monitors and single sensors under variable indoor air quality and thermal conditions, Build. Environ., 187, (2021)

[6]

Khan D.S., Kolarik J., Weitzmann P., Design and application of occupant voting systems for collecting occupant feedback on indoor environmental quality of buildings–a review, Build. Environ., 183, (2020)

[7]

Zhao Y., Li D., Multi-domain indoor environmental quality in buildings: a review of their interaction and combined effects on occupant satisfaction, Build. Environ., 228, (2023)

[8]

Jayathissa P., Quintana M., Abdelrahman M., Miller C., Humans-as-a-sensor for buildings—intensive longitudinal indoor comfort models, Buildings, 10, 10, (2020)

[9]

Becerik-Gerber B., Lucas G., Aryal A., Awada M., Berges M., Billington S.L., Boric-Lubecke O., Ghahramani A., Heydarian A., Jazizadeh F., Ten questions concerning human-building interaction research for improving the quality of life, Build. Environ., 226, (2022)

[10]

Dykes C., Baird G., A review of questionnaire-based methods used for assessing and benchmarking indoor environmental quality, Intell. Build. Int., 5, 3, pp. 135-149, (2013)

← 1 2 3 4 5 6 7 →