VIRTUAL: Livable Cities – New York

Abstract

This research aims to develop a framework to evaluate occupant feedback on Indoor Air Quality (IAQ) across communities. The framework brings big text data from social media (herein Tweeter) and develops an emotion artificial intelligence (AI) model based on Natural Language Processing (NLP) approach to evaluate occupant sentiment (satisfaction/dissatisfaction) on the IAQ level in buildings. For sentiment analyses, we applied QDAP dictionary which involves 11 emotion metrics including anger, anticipation, disgust, fear, joy, negative, positive, sadness, surprise, trust. We tested the framework for New York City, NY during 2021. We implemented data acquisition, modeling, and visualization using RStudio as the primary computational platform. Findings suggest that occupant sentiment on IAQ varies across urban zones, depending on socioeconomic and demographic structure of the city. This research aids architects, planners, and policymakers to understand the IAQ experience in buildings by better understanding the human context of neighborhoods in order to advance site-specific design solutions and ensure health and resilience goals of future cities.