[Paper Review] Leveraging Data Driven Approaches to Quantify the Impact of Construction Projects on Urban Quality of Life

Zhengbo Zou, Semiha Ergan|arXiv (Cornell University)|Jan 25, 2019

Occupational Health and Safety Research62 references4 citations

TL;DR

This paper proposes a data-driven framework to quantify construction projects' impacts on urban quality of life using open data from New York City. By analyzing 311 service requests and 27 road projects, it identifies rising complaints over time—especially noise, air quality, and sanitation—and achieves an R-squared of 0.67 in predicting complaint trends via machine learning models.

ABSTRACT

According to the World Bank, more than half of the world's population now lives in cities, creating burdens on the degraded city infrastructures and driving up the demand for new ones. Construction sites are abundant in already dense cities and have unavoidable impacts on surrounding environments and residents. However, such impacts were rarely quantified and made available to construction teams and local agencies to inform their planning decisions. A challenge in achieving this was the lack of availability of data that can provide insights about how urban residents respond to changes in their environment due to construction projects. Wider availability of data from city agencies nowadays provides opportunities for having such analysis possible. This paper provides the details of a generic data-driven approach that enables the analysis of impact of construction projects on quality of life in urban settings through the quantification of change on widely accepted quality of life indicators in cities. This paper also evaluated the approach using data from publicly construction projects' information and open city data portals from New York City. Historical 311 Service Requests along with 27 road reconstruction projects were used as testbeds. The results showed that 61% of the projects analyzed in this testbed experienced higher 311 requests after the commencement of construction, with main complaints of 'noise', 'air quality', and 'sewer' at the beginning of construction, and 'sanitation' and 'waste' towards the end. Prediction models, built using regression machine learning algorithms, achieved an R-Squared value of 0.67. The approach is capable of providing insights for government agencies and construction companies to take proactive actions based on expected complaint types through different phases of construction.

Motivation & Objective

• To address the lack of quantified data on how construction projects affect urban residents' quality of life.
• To identify and analyze resident complaints related to construction through publicly available urban data.
• To develop a scalable, data-driven methodology for assessing construction impacts across different project phases.
• To enable proactive planning by construction teams and city agencies using predictive insights.
• To validate the approach using real-world data from New York City’s 311 service requests and road reconstruction projects.

Proposed method

• Utilizes historical 311 service requests as a proxy for resident complaints related to construction activities.
• Integrates open data from city portals, including project start dates, locations, and durations for 27 road reconstruction projects.
• Applies time-series analysis to track changes in complaint volumes before, during, and after construction phases.
• Employs regression-based machine learning models to predict complaint types and volumes based on project timelines and characteristics.
• Classifies complaints into categories such as noise, air quality, sanitation, waste, and sewer issues using natural language processing on 311 request texts.
• Validates model performance using R-squared metrics to assess predictive accuracy of complaint trends.

Experimental results

Research questions

• RQ1 How do construction projects influence resident complaints related to urban quality of life over time?
• RQ2 Which types of complaints (e.g., noise, air quality, sanitation) are most prevalent at different stages of construction?
• RQ3 To what extent can machine learning models predict the volume and type of complaints based on project data?
• RQ4 Can open data sources like 311 service requests reliably reflect the impact of construction on urban residents?
• RQ5 What are the key indicators of declining urban quality of life during different phases of construction projects?

Key findings

• 61% of the 27 road reconstruction projects analyzed generated a higher volume of 311 service requests after construction began.
• Noise, air quality, and sewer complaints were most frequent at the start of construction projects.
• Sanitation and waste-related complaints increased significantly toward the end of construction projects.
• Machine learning prediction models achieved an R-squared value of 0.67 in forecasting complaint trends across project phases.
• The data-driven approach successfully identified temporal patterns in resident complaints, enabling phase-specific impact assessment.
• The integration of 311 data with project metadata provides a scalable, actionable method for urban planning and construction management.