Frequent public health emergencies (PHEs) impact urban resilience and threaten sustainable development. In view of the differing focuses on resilience and sustainability, the paper considered long-term sustainable development while assessing short-term urban resilience. Due to close cooperation among social structures, this paper viewed social structures as symbiotic units and evaluated sustainable urban resilience under PHEs based on symbiotic theory. To address evaluation uncertainty, a data-driven weighting approach was proposed. Additionally, empirical research was conducted on five major cities in Sichuan, a heavily affected province during COVID-19. Finally, Overall recommendations and city-specific suggestions were put forward to enhance resilience.

Urban instant-delivery platforms increasingly require efficient, punctual, and low-carbon delivery services. Unmanned aerial vehicles (UAVs) can reduce dependence on congested ground traffic in meal delivery and further improve overall delivery efficiency through coordinated operations with ground riders at rendezvous points. However, existing studies mainly focus on ground-based routing or simplify UAV-assisted delivery as a single-objective problem, limiting their ability to balance cost, completion time, carbon emissions, and service quality. To address this limitation, this paper investigates a collaborative UAV–rider meal delivery routing problem and formulates a multi-objective optimization model integrating restaurant pickup, UAV transfer, rider last-mile delivery, and soft customer time windows. An Enhanced NSGA-II algorithm is then developed, where hybrid initialization improves solution quality and diversity, adaptive operators balance exploration and exploitation, local search refines route structures, structural repair maintains feasibility, and diversity preservation supports a well-distributed Pareto front. Comparative experiments against NSGA-II, MOPSO, NSGA-III, MOEA/D, MODE, and IMODE, together with scalability, ablation, sensitivity, and case analyses, show that E-NSGA-II provides stronger Pareto-front approximation. The results support its use as a decision-support method for service-aware and low-carbon UAV–rider meal delivery, while also revealing additional computational cost.

The world has seen a substantial number of disastrous emergencies, which lead to heated discussion on the Internet and then chaos without proper interference. Motivated by others’ emotions through online discussion, netizens actively interact with each other and flock together, eventually reaching to the same emotional state. That's what emotion polarization means. To guide the netizens, influencing factors accounting for emotion polarization must be identified. In this paper, we take the China Eastern Airlines MU5735 crash as an example. All the hot topics,comments and retweets concerning the air crash on Sina Weibo are collected by a web crawler from March 21 to April 1, 2022. The reciprocal of sentiment entropy is first used to measure emotion polarization. 7 main factors affecting emotion polarization are identified based on Hovland's Persuasion Model. In order to mine key influencing factors, four machine learning models are established and tuned, among which Adaptive Boosting regression model (AdaBoost) has the best performance. Then three influencing factors are mined by feature importance ranking of AdaBoost. By SHapley Additive exPlanations (SHAP), a more concise outcome of feature importance ranking is represented. Finallly, according to the figures of feature importance ranking, decision-making suggestions on facilitating emotion polarization is proposed.