TSYS School's Amjad Hossain Investigates Factors Influencing Accidents at Roadway Work Zones

Although construction (maintenance) of roadway infrastructure promotes social and economic development and improves traffic safety, roadway work zones (WZs) present safety issues for construction workers and travelers and adversely affect vehicular movement. New research by TSYS School computer scientist Amjad Hossain and colleagues from the Wisconsin Department of Transportation, the Baltimore Metropolitan Council, Bradley University, the University of Oklahoma, the University of North Carolina - Charlotte and the University of Wisconsin - Milwaukee collect and analyze Twitter data (currently “X” threads) in order to explore public perceptions of roadway work zones and to identify factors that influence crashes and other public experiences at roadway work zones. To do so they employed several machine learning methods to classify roadway work zone-related tweets and then performed exploratory, sentiment, and emotional analyses of the classified tweets. Next, they verified their Twitter-related research outcomes using police crash reports. Sentiment and emotion analysis using classified tweets (with a 92% classification accuracy) showed somewhat negative emotions towards roadway work zones and onsite physical elements. However, the overall sentiment and emotion scores support the positive outcomes of roadway work zone activities. The study, which is set to appear in a future issue of Data Science and Management, also found a strong temporal relationship between roadway work zone-related tweets and fatalities. A cross-analysis of tweets and crash reports revealed that certain physical elements (e.g., signs, barriers, barrels, closures, and workers) are strongly associated with severe crashes at roadway work zones. The results of their study may help policymakers develop improved driving experiences and reduce roadway work zone-related traffic accidents.