Exploring U.S. Occupant Perception Toward Indoor Air Quality Via Social Media and NLP Analysis
Author(s): Mehdi Ashayeri, Soroush Piri, Narjes Abbasabadi.
The global implementation of stay-at-home mandates altered people's activities within the built environment, prompting a slowdown in the spread of covid viruses. Nevertheless, this period shed light on previously unforeseen challenges in achieving "better" indoor air quality (IAQ) within buildings, necessitating a focus on building health resilience for future scenarios. This study aims to evaluate occupants' feedback on the impact of stay-at-home measures on IAQ perception in buildings across the U.S. during the first year of the pandemic (2020) and compare it with the baseline from the previous year (2019) nationwide to assess the changes and identify potential areas for IAQ management strategies. Geo-tagged textual data from X (formerly known as Twitter) platform were collected and analyzed using Natural Language Processing (NLP) based on time series sentiment analysis techniques to compute the feedback. Findings indicate that occupants’ negative feedback on IAQ increased during 2020 compared to the baseline. It was also found that public perception of IAQ in 2020 was notably less favorable, potentially due to deteriorating conditions inside homes as people spent more time indoors. The study underscores the potential of NLP in capturing occupant perception, contributing to data-driven studies that can inform design, engineering, and policy-making for sustainable future.