COVID-19: Understanding Construction Industry Responses on Twitter in the Emergence of Novel Coronavirus

COVID-19 has spread rampantly in 2020 and people in different countries experienced unprecedented challenges to respond immediately. It has deeply shaken different industries and the overall economy. Many businesses were closed during this disease outbreak, but the construction industry continued to operate while others struggled. As the pandemic spread, the intensity of social media interactions dramatically increased as people started maintaining physical distances and staying at home. Recent studies have shown that social media serves the purpose of disseminating information in major crises and such social interactions correlate with what happens in the real world. Unlike traditional media, social media data also offered sufficient statistical power to understand risk communication patterns. The construction industry adopted innovative strategies to continue its operations and activities while responding to a number of concerns associated with health risks of the workers on site. This study aims at identifying the emerging communication patterns of construction stakeholders on social media (Twitter) during COVID-19. Around 12 million tweets were collected in the early days of the ongoing pandemic (March, April, and May 2020) by Twitter Application Programming Interface (API), in the region of North America; then filtered this data based on keywords pertaining to COVID-19 and construction activities. Such information was processed by applying several machine learning and natural language processing techniques. The spatiotemporal patterns of construction risk communication revealed in this study would support policymakers, businesses, and other industries to take more efficient measures and be more resilient both in the current and future pandemics.