Shared mobility is growing rapidly and changing the mobility landscape. The COVID-19 pandemic has complicated travel mode choice behavior in terms of shared mobility, but the evidence on this impact is limited. To fill this gap, this paper first designs a stated preference survey to collect mode choice data before and during the pandemic. Different shared mobility services are considered, including ride hailing, ride sharing, car sharing, and bike sharing. Then, latent class analysis is used to divide the population in terms of their attitudes toward shared mobility. Nested logit models are applied to compare travel mode choice behavior during the two periods. The results suggest that shared mobility has the potential to avoid the high transmission risk of public transport and alleviate the intensity of private car use in the COVID-19 context, but this is limited by anxiety about shared spaces. As the perceived severity of the pandemic increases, preference for ride hailing and ride sharing decreases, and a price discount for ride hailing is more effective than that for ride sharing at maintaining the ridership despite the impact of COVID-19. These findings contribute to understanding the change in travel demand and developing appropriate strategies for shared mobility services to adapt to the pandemic.

The car purchase intention of noncar owners is closely related to the growth of car ownership and may be changed in the context of COVID-19. This paper aims to investigate the decision-making mechanism of the car purchase intention before COVID-19 and the change of car purchase intention after COVID-19. The contributions of influencing factors are derived from the gradient boosting decision tree model and the asymmetric effects of attitudinal factors are further analyzed based on the three-factor theory. The comprehensive importance hierarchies of the two dependent variables are constructed through the integrated analysis of impact range and impact asymmetry. The results show that people who were previously more willing to buy cars are more likely to increase their willingness to buy after COVID-19. The pre–COVID-19 car purchase intention is primarily determined by shared mobility-related attitudes, while attitudes toward private car use have a greater impact on the post–COVID-19 intention change. These two attitudes are mainly manifested as intention relievers and discouragers before COVID-19, but they are more likely transformed into intention strengtheners and encouragers after COVID-19. The availability of shared mobility has the maximum comprehensive importance to the post–COVID-19 intention change. Therefore, maintaining and promoting the ridership of shared mobility will be the most important prerequisite for alleviating the car purchase intention after COVID-19 pandemic.

Although trip purpose inference based on passively collected data has long been investigated, less attention has been paid to inter-city trips. The reason is, except using ticket sales data, only limited trips can be extracted due to the lower frequency of inter-city trips during daily life. However, for ticket sales data, only limited features can be explored due to the lower spatial resolution of trajectories. Therefore, this paper endeavoured to exploit the potential of ticket sales data from the perspective of the group. Theoretically, by introducing concepts of text mining, the trip purpose of a group can be viewed as analogous to the topics of a document. Trip purpose was characterized by a time topic model (TTM) that incorporates start time, in contrast to latent Dirichlet allocation (LDA). This approach was implemented via a three-step method. First, groups were reconstructed from tickets. Second, three types of features, i.e., demographic, experience and co-travel network features, were extracted as a series of words to describe passengers. Third, trip purposes were automatically clustered based on the co-occurrence of words in the same group using a TTM. This paper presents comparison experiments to evaluate feature sets and the model performance based on a web-based travel survey, including the ground truth. Moreover, this paper highlights the practical use of a TTM to detect anomalies beyond anticipated trip purpose based on large-scale ticket sales data collected from Beijing, China. The full feature set was found to be preferable since both precision and recall increased when demographic and co-travel network features were considered. Meanwhile, the TTM produced robust and balanced predictions and exhibited additional power to recognize personal business compared with baseline methods.

Extraction of traffic features constitutes a key research direction in traffic safety planning. In previous traffic tasks, road network features are extracted manually. In contrast, Network Representation Learning aims to automatically learn low-dimensional node representations. Enlightened by feature learning in Natural Language Processing, representation learning of urban nodes is studied as a supervised task in this paper. Following this line of thinking, a deep learning framework, called StreetNode2VEC, is proposed for learning feature representations for nodes in the road network based on travel routes, and then model parameter calibration is performed. We explain the effectiveness of features from visualization, similarity analysis, and link prediction. In visualization, the features of nodes naturally present a clustered pattern, and different clusters correspond to different regions in the road network. Meanwhile, the features of nodes still retain their spatial information in similarity analysis. The proposed method StreetNode2VEC obtains a AUC score of 0.813 in link prediction, which is greater than that obtained from Graph Convolutional Network (GCN) and Node2vec. This suggests that the features of nodes can be used to effectively and credibly predict whether a link should be established between two nodes. Overall, our work provides a new way of representing road nodes in the road network, which have potential in the traffic safety planning field.

This paper proposes a novel approach to identify the key nodes and sections of the roadway network. The taxi-GPS trajectory data are regarded as mobile sensor to probe a large scale of urban traffic flows in real time. First, the urban primary roadway network model and dual roadway network model are developed, respectively, based on the weighted complex network. Second, an evaluation system of the key nodes and sections is developed from the aspects of dynamic traffic attributes and static topology. At the end, the taxi-GPS data collected in Xicheng District of Beijing, China, are analyzed. A comprehensive analysis of the spatial-temporal changes of the key nodes and sections is performed. Moreover, the repetition rate is used to evaluate the performance of the identification algorithm of key nodes and sections. The results show that the proposed method realizes the expression of topological structure and dynamic traffic attributes of the roadway network simultaneously, which is more practicable and effective in a large scale.