Traffic congestion and accidents take a toll on commuters' daily experiences and society. Locating the venues prone to congestion and accidents and capturing their perception by public members is invaluable for transport policy-makers. However, few previous methods consider user perception toward the accidents and congestion in finding and profiling the accident- and congestion-prone areas, leaving decision-makers unaware of the subsequent behavior responses and priorities of retrofitting measures. This study develops a framework to identify and characterize the accident- and congestion-prone areas heatedly discussed on social media. First, we use natural language processing and deep learning to detect the accident- and congestion-relevant Chinese microblogs posted on Sina Weibo, a Chinese social media platform. Then a modified Kernel Density Estimation method considering the sentiment of microblogs is employed to find the accident- and congestion-prone regions. The results show that the 'congestion-prone areas' discussed on social media are mainly distributed throughout the historical urban core and the Northwest of Pudong New Area, in reasonably good agreements with actual congestion records. In contrast, the 'accident-prone areas' are primarily found in locations with severe accidents. Finally, the above venues are characterized in spatio-temporal and semantic aspects to understand the nature of the incidents and assess the priority level for mitigation measures. The outcomes can provide a reference for traffic authorities to inform resource allocation and prioritize mitigation measures in future traffic management.

Urban rail development can increase land value, reduce commute time, and increase accessibility, as reported in the literature. However, little is known about the impact of opening urban rail transit stations on people's sentiment, particularly in the context of large metropolises where population density is significantly high. This paper investigates such impact by studying six new transit stations opened in Hong Kong. People's sentiment and activity in station nearby areas are estimated by tweet sentiment and tweet activity. We use the difference-in-difference model to study the impact of opening new transit stations. Tweet sentiment, tweet activity, tweet content, and footprints of people who visit the station-influenced area ‘before and after’ the opening of transit stations are analyzed. The results suggest that, in general, the introduction of transit stations causes a positive change in tweet activity, and the change is statistically significant after six months. Regarding tweet sentiment, new transit stations tend to pose a mixed effect in a short-term, a positive influence on areas with high-density residential places, yet a negative influence on areas with a large proportion of nature reserve areas. These short-term effects, positive or negative, become not significant in the long term (after twelve months). Our analysis also confirmed that the introduction of new transit stations increased accessibility from (to) other parts of the city to(from) the station's nearby area, which was shown by the expanded locations sustaining users visited. These findings indicate that the urban rail transit system in Hong Kong promotes more active neighborhoods yet does not always promotes positive influence on people's sentiment. Further studies are needed to make future urban rail transit systems promoting active and happy neighborhoods. The study is relevant to the Belt and Road Initiative (BRI) in methodologies, data, and findings. The social media analysis method used in this study, including text mining and sentiment analysis, can be easily extended to multiple language analysis for Singapore, Malaysia, as well as other regions in the belt and road plan. The developed tools could contribute to analyzing the influence of cross-country projects on local neighborhoods in the belt and road plan.