Author:
Do Sy Tien,Nguyen Viet Thanh,Banlasan Denver
Abstract
Purpose
This study aims to use social media data mining to revitalize and support existing urban infrastructure monitoring strategies by extracting valuable insights from public opinion, as current strategies struggle with issues such as adaptability to changing conditions, public engagement and cost effectiveness.
Design/methodology/approach
Twitter messages or “Tweets” about public infrastructure in the Philippines were gathered and analyzed to discover reoccurring concerns in public infrastructure, emerging topics in public debates and the people’s general view of infrastructure services.
Findings
This study proposes a topic model for extracting dominating subjects from aggregated social media data, as well as a sentiment analysis model for determining public opinion sentiment toward various urban infrastructure components.
Originality/value
The findings of this study highlight the potential of social media data mining to go beyond the limitations of traditional data collection techniques, as well as the importance of public opinion as a key driver for more user-involved infrastructure management and as an important social aspect that can be used to support planning and response strategies in routine maintenance, preservation and improvement of urban infrastructure systems.
Subject
Building and Construction,Architecture,Civil and Structural Engineering,General Computer Science,Control and Systems Engineering
Reference61 articles.
1. Integration of social media in day-to-day operations of construction firms;Journal of Management in Engineering,2019
2. Data mining in social media,2011
3. Latent dirichlet allocation;Journal of Machine Learning Research,2003
4. Review paper: health monitoring of civil infrastructure;Structural Health Monitoring,2003