The indoor environment significantly impacts human health and well-being; enhancing health and reducing energy consumption in these settings is a central research focus. With the advancement of Information and Communication Technology (ICT), recommendation systems and reinforcement learning (RL) have emerged as promising approaches to induce behavioral changes to improve the indoor environment and energy efficiency of buildings. This study aims to employ text mining and Natural Language Processing (NLP) techniques to thoroughly examine the connections among these approaches in the context of human-building interaction and occupant context-aware support. The study analyzed 27,595 articles from the ScienceDirect database, revealing extensive use of recommendation systems and RL for space optimization, location recommendations, and personalized control suggestions. Furthermore, this review underscores the vast potential for expanding recommender systems and RL applications in buildings and indoor environments. Fields ripe for innovation include predictive maintenance, building-related product recommendation, and optimization of environments tailored for specific needs, such as sleep and productivity enhancements based on user feedback. The study also notes the limitations of the method in capturing subtle academic nuances. Future improvements could involve integrating and fine-tuning pre-trained language models to better interpret complex texts.

It's not just the models, techniques, or technologies that improve building performance; the digital skills of built environment professionals also play a significant part. The deluge of data from buildings, intelligent systems, and simulation tools is well-documented, and like other domains, building design, construction, and operations professionals are keen to learn skills like Python scripting that are common to the data science communities. This paper analyzes a massive open online course on the edX platform called Data Science for Construction, Architecture, and Engineering. This course was launched in April 2020, and it combines building science concepts with beginner-level data science skills, such as using Python and the essential libraries of Pandas, Sci-kit Learn, and Seaborn. This paper presents an analysis of the demographics and geographic data from 18,600 participants and survey results from 126 out of 1,561 verified course users. The survey focused on the experience of course participants and suggestions for improvement. This information can aid other data science educators in developing content to better educate built environment professionals.

Hybrid working strategies have become, and will continue to be, the norm for many offices. This raises two considerations: newly unoccupied spaces needlessly consume energy, and the occupied spaces need to be effectively used to facilitate meaningful interactions and create a positive, sustainable work culture. This work aims to determine when spontaneous, collaborative interactions occur within the building and the environmental factors that facilitate such interactions. This study uses smartwatch-based micro-surveys using the Cozie platform to identify the occurrence of and spatially place interactions while categorizing them as a collaboration or distraction. This method uniquely circumvents pitfalls associated with surveying and qualitative data collection: occupant behaviors are identified in real-time in a non-intrusive manner, and survey data is corroborated with quantitative sensor data. A proof-of-concept study was deployed with nine hybrid-working participants providing 100 micro-survey cluster responses over approximately two weeks. The results show the spontaneous interactions occurring in hybrid mode are split evenly among the categories of collaboration, wanted socialization , and distraction and primarily occur with coworkers at one’s desk. From these data, we can establish various correlations between the occurrence of positive spontaneous interactions and different factors, such as the time of day and the locations in the building. This framework and first deployment provide the foundation for future large-scale data collection experiments and human interaction modeling.