Proposed a natural language processing method to assess occupants' satisfaction 2) Identified 3 topic clusters (transportation & location, running cost, and health & wellbeing) 3) The median satisfaction with LEED and non-LEED apartments is positive. 4) A significant but small or negligible uptick in satisfaction with LEED apartments 5) There is a weak relationship between rent price and star rating.
Leadership in Energy and Environmental Design (LEED) certified buildings aim to offer a sustainable and healthy built environment. Previous studies have shown mixed and inconsistent results on whether occupants in LEED-certified buildings are more satisfying than in non-LEED-certified counterparts. Those studies usually based on surveys or questionnaires for commercial buildings were limited by sample size and pre-defined question structures. Since most people stay longer at home during the COVID-19 pandemic and the trend might continue in the post-pandemic era, assessing the satisfaction with LEED-certified residential buildings benefits future environmental design and certification system development. In this work, we propose a natural language processing-based approach for such assessment. The study collected 16,761 online reviews on 260 LEED-certified apartments and 180 non-LEED-certified-apartments from social media, then applied topic modeling and sentiment analysis to evaluate occupants’ satisfaction. Based on topic modeling, we categorized online comments into three topic clusters, 1) location and transportation, 2) running cost, and 3) health and wellbeing. The subsequent sentiment analysis has shown a statistically significant but small or negligible enhancement in the satisfaction occurring in LEED-certified apartments compared to non-LEED-certified ones concerning all the three topic clusters. The “significant but small or negligible uptick” has also been found in online star rating and indoor environmental satisfaction. The only exception with a large effect size is lighting that is significantly more satisfying in LEED-certified apartments. Nevertheless, the statistical significance in online star rating disappears when it is normalized by rent price and property house value.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.