Search

This study investigates the extent and persistence of major crisis events in the crude oil market and economy and searches for general rules of event impact. Although the short-term effects of such crises may quickly become evident, their long-term implications can be challenging to uncover. To this end, we analyzed 50 major crisis events across four categories using a Proxy structural vector autoregressive (Proxy-SVAR) model. The results show that these events substantially impacted crude oil production, world crude oil prices, and inflation in China and the United States. Generally speaking, major crisis events have a more severe impact on the crude oil market, but their impact on the economy lasts longer. Notably, geopolitical conflicts have led to a sharp decline in S&P500, resulting in a simultaneous reduction in the industrial production indices of the world, China, and the US. Among the different types of crises, the financial crisis had the most prolonged impact, persisting for approximately four years. The public health emergency represented by COVID-19 resulted in a decline in actual oil prices, with its impact on the oil market continuing for over three years. Considering our findings, we suggest four policy measures to enhance economic resilience. [ABSTRACT FROM AUTHOR]

Bike-sharing system has become an indispensable element of sustainable urban transportation, effectively resolving the "last mile" transportation challenge for city dwellers. A major daily operational task in these systems is planning a fleet to rebalance the bikes over time, ensuring the optimal availability of bikes and docks to users. Recycling is also a daily work with the an increase in the number of broken bikes. However, rebalancing or recycling operation is always regarded as an independent tasks. They are separately studied in existing papers. Thus, this paper develops an operational strategy for recycling broken bikes during the rebalancing process, and studies the combination of the station inventory and vehicle routing problems. First, an inventory routing model is constructed with the aim of minimizing the total costs including procurement, expected user loss, inventory and transportation costs. Then, a two-stage iterative algorithm is developed with both exact and heuristic algorithms. We use real-world data from Capital Bikeshare to test our proposed model and approach, which shows the two-stage iterative algorithm is efficient and outperforms existing solutions in reducing total costs. Finally, the sensitivity analysis is performed on key parameters such as the vehicle's capacity, unit penalty costs for customer dissatisfaction events, unit inventory holding costs and the observation period of rebalancing. It shows that enterprises can reduce the total cost by altering vehicle's capacity, reducing the unit inventory holding costs or changing the observation period of rebalancing. [ABSTRACT FROM AUTHOR]

Due to the strong nonlinearity and high complexity of foreign exchange rate data, how best to accurately analyze their trends and forecast them is regarded as a challenging research topic. While such research has developed rapidly and a large number of publications have appeared, few programmatic quantitative and qualitative overviews have been compiled in the field of exchange rate. By integrating bibliometric methods with network visualization based on CiteSpace software, this study analyzed 4999 publications of exchange rate research from the Web of Science (WoS) Core Collection database during 1992 to 2021. The study summarizes the major development in exchange rate determination since Meese‐Rogoff puzzle, from New Open‐Economy Macroeconomics (NOEM) and the Foreign Exchange Market Micro‐Structure Hypotheses, to determination model based on relationship between exchange rate and commodity price. Through the study's statistical analysis, co‐occurrence, co‐citation, and co‐keywords analysis, the influential authors, research institutions, countries and regions, journals, research hotspots, and future trends in the field of exchange rate are intellectually identified over the past 30 years. As a complement to existing literature, this paper provides theoretical and practical reference for researchers and practitioners in the field of exchange rate. [ABSTRACT FROM AUTHOR]

Church tourism has gained popularity due to the historical, artistic, and religious significance of churches, contributing significantly to the social and economic sectors. The destination image of churches plays a crucial role in tourism marketing. However, existing literature predominantly relies on traditional methods to study tourists' perception of churches as tourism destinations, with limited analysis of user‐generated content (UGC) like online reviews. This study aims to fill this gap by analyzing the online reviews of 10 renowned European churches posted on TripAdvisor using text mining techniques. Findings reveal that tourists mainly focus on overall description, visiting experience, architectural design, and surrounding environment of the church, with specific areas of interest for certain churches. The research findings can assist church administrators in formulating sustainable tourism strategies and promoting the development of the church tourism. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is currently one of the most prominent fields in the technology industry, with China and the US being two global centers for AI research and development. However, the two countries differ in their development levels of the AI industry. In particular, the emergence of ChatGPT in 2022 has sparked extensive discussions regarding the capabilities and competitiveness of Chinese AI companies. This study analyzes over 120 000 AI invention patents approved in the past five years in both China and the US. Firstly, it constructs a multidimensional index based on AI patent features to identify the top 10 AI companies in both countries. Further, the analysis reveals significant differences in patent technology and research networks between these two groups. Chinese leading companies have notably fewer AI patents, less patent citation, and lower conversion rates. The patents of leading Chinese companies are mainly concentrated on application-level technologies such as image recognition and speech recognition, and have not yet formed distinctive AI technology clusters. In contrast, American leading companies have generated more influential AI patents, particularly forming multiple technology clusters in the foundational and core technology layers of the AI industry. In terms of academic research, Chinese leading companies primarily collaborate with domestic research institutions, while American leading companies demonstrate stronger collaboration with Chinese institutions, as well as among domestic companies. This comparative analysis reveals prominent differences in technological capabilities and collaboration strategies of leading AI companies in China and in the US, and provides managerial insights and three policy suggestions for better developing China's AI industry. [ABSTRACT FROM AUTHOR]

Background: The management of patients with disorders of consciousness (DOC) presents substantial challenges in clinical practice. Deep brain stimulation (DBS) has emerged as a potential therapeutic approach, but the lack of standardized regulatory parameters for DBS in DOC hinders definitive conclusions. Objective: This comprehensive review aims to provide a detailed summary of the current issues concerning patient selection, target setting, and modulation parameters in clinical studies investigating the application of DBS for DOC patients. Methods: A meticulous systematic analysis of the literatures was conducted, encompassing articles published from 1968 to April 2023, retrieved from reputable databases (PubMed, Embase, Medline, and Web of Science). Results: The systematic analysis of 21 eligible articles, involving 146 patients with DOC resulting from acquired brain injury or other disorders, revealed significant insights. The most frequently targeted regions were the Centromedian‐parafascicular complex (CM‐pf) nuclei and central thalamus (CT), both recognized for their role in regulating consciousness. However, other targets have also been explored in different studies. The stimulation frequency was predominantly set at 25 or 100 Hz, with pulse width of 120 μs, and voltages ranged from 0 to 4 V. These parameters were customized based on individual patient responses and evaluations. The overall clinical efficacy rate in all included studies was 39.7%, indicating a positive effect of DBS in a subset of DOC patients. Nonetheless, the assessment methods, follow‐up durations, and outcome measures varied across studies, potentially contributing to the variability in reported efficacy rates. Conclusion: Despite the challenges arising from the lack of standardized parameters, DBS shows promising potential as a therapeutic option for patients with DOC. However, there still remains the need for standardized protocols and assessment methods, which are crucial to deepen the understanding and optimizing the therapeutic potential of DBS in this specific patient population. [ABSTRACT FROM AUTHOR]

Tourism has become a major driver of China's economic growth and consumes much energy causing environmental pollution problems. This paper combines the LMDI (logarithmic mean Divisia index) method and K-means clustering to analyze the factors influencing tourism energy consumption in seven Chinese provinces and discusses strategies for energy consumption in tourism. Specifically, firstly, this paper decomposes the tourism energy consumption factors in each province into six factors and identifies the driving forces of different factors on energy consumption. Secondly, K-means clustering method is used to classify different provinces into three categories using the latest dynamic influencing factors as clustering factors and provincial targeted suggestions are made according to the characteristics of different categories. This paper combines the LMDI model with cluster analysis to find targeted energy optimization strategies for the energy consumption of the Chinese tourism industry. [ABSTRACT FROM AUTHOR]

Mining diamond poses significant and potentially underestimated risks to the environment worldwide. Here, we propose a Diamond Environmental Impacts Estimation (DEIE) model to forecast the environmental indicators, including greenhouse gas (GHG) emissions, mineral waste, and water usage of the diamond industry from 2030 to 2100 in the top diamond production countries under different Shared Socio-economic Pathways (SSPs). The DEIE projection results indicate that the annual GHG emissions, mineral waste, and water usage of the global diamond industry will reach 9.65 Mt, 422.80 Mt, and 78.68 million m3 under the SSP1-1.9 scenario, and 13.26 Mt, 582.84 Mt, and 107.95 million m3 under the SSP2-2.6 scenario in 2100, respectively. We analyze the environmental impact heterogeneities and the associated driving factors across the major diamond production countries identified by our DEIE framework. In addition, we find that lab-grown diamonds can reduce annual GHG emissions, mineral waste, and water usage by 9.58 Mt, 421.06 Mt, and 66.70 million m3 in 2100. The lab-grown diamond substitution policy can annually save 714 million cubic meters of landfill space, harvest 255 million kilograms of rice, feed 436 million people, and lift 1.19 million households out of hunger. The lab-grown diamond substitution policy could contribute to the diamond industry's GHG mitigation and sustainability efforts in a cost-saving manner. [ABSTRACT FROM AUTHOR]

The global tourism industry is struggling to recover from the COVID-19 pandemic. During the COVID-19 pandemic, daily tourism forecasting is more critical than ever before in supporting decisions and planning. Considering the changes in tourist psyche and behaviour caused by COVID-19, this study attempts to investigate whether the statistical modelling methods can work reliably under the new normal when travel restrictions are eased or lifted. To this end, we first compare the predictivity of daily tourism demand data before and during COVID-19, and observe heterogeneous impacts across different geographical scales. Then an improved multivariate & multiscale decomposition-ensemble framework is proposed to forecast daily tourism demand. The empirical study indicates the superiority and practicability of the proposed framework before and during COVID-19. Finally, we call for more research on the comparability of tourism demand forecasting. [ABSTRACT FROM AUTHOR]

The authors aim to interpret human and AI interactions from the decision perspective. The authors decompose the interaction analysis into the following main components in the context of interactions: Individual behavior patterns, interaction relationships, and comprehensive analysis. The authors interpret intertemporal decisions from a physical perspective and employ cross-discipline concepts and methodologies to extract the behavior characteristics of players in the empirical case study. About the individual behavior patterns, the authors find that human players prefer short-term periods to AI in decision-making. The interaction relationship analysis reveals a dynamic relationship between possible short-term co-movement and nearly counter-movement in the long run. The authors apply principal component analysis to descriptive indicators and discover a regular decision hierarchy. The main behavior pattern of players in the game of Go is switching between careful and daring behaviors. The differences in the decision hierarchies imply a discrepancy of patience between humans and AI. [ABSTRACT FROM AUTHOR]

Purpose: This study explores the contagion of greenwashing strategies among ESG mutual funds. It investigates how the greenwashing behaviors of peer funds within the same family influence a fund's decision to engage in greenwashing. The research also examines the impact of greenwashing on genuine ESG funds and explores the mechanisms through which greenwashing strategies spread across ESG mutual funds. Design/methodology/approach: This paper employs a two-stage least squares regression model with cross-fund returns standard deviation as an instrumental variable to disentangle the peer effects of greenwashing from family-level characteristics. The analysis incorporates various fund characteristics and introduces four contagion channels through which greenwashing may influence genuine ESG funds. Findings: The study finds greenwashing behavior in ESG funds is positively influenced by similar practices within their fund family. Larger assets under management and older funds with higher management fees show resilience against greenwashing influences, while team-managed funds are more susceptible. Additionally, socially responsible investors struggle to distinguish between genuine and greenwashing ESG funds, which may contribute to the persistence of greenwashing practices. Originality/value: This paper contributes to the literature by delineating the mechanisms of greenwashing contagion within ESG mutual funds. It also examines the demand-side incentives for adopting greenwashing strategies, offering insights into the implications for fund flows and investor behavior. This study is among the first to analyze the contagion effects of greenwashing strategies across an extensive network of ESG funds, enriching our understanding of the broader impacts of greenwashing in the context of socially responsible investing. [ABSTRACT FROM AUTHOR]

The assessment of credit risk for P2P lending platform applicants is critical to investors. Feature engineering is an essential technique in distilling classification knowledge during the credit risk prediction data preprocessing stage. Although previous literature used feature selection methods to identify key features, feature transformation is more useful in discovering intrinsic nonlinear characteristics in credit data. In this study, we propose a synthetic multiple tree‐based feature transformation method to generate features. Multiple tree‐based feature transformation methods are employed and fused to acquire a new feature set. The bagging‐based tree ensemble feature transformation method (Bagging‐TreeEnsembleFT) and boosting‐based tree ensemble feature transformation method (Boosting‐TreeEnsembleFT) are two types of feature transformation methods that we specifically propose to validate their effect. We verify the credit risk prediction performance using the proposed synthetic feature transformation methods on real P2P Lending credit datasets. Empirical analysis demonstrates that tree‐based ensemble feature transformation methods with boosting ensemble strategy achieve better prediction performance on various datasets corresponding to different partitions and class distributions compared to tree‐based ensemble feature transformation methods with bagging ensemble strategy and individuals. Moreover, the proposed synthetic feature transformation method improves the credit risk prediction performance in terms of accuracy, AUC, and F1‐score. [ABSTRACT FROM AUTHOR]

Developing effective strategies to earn excess returns in the stock market is a cutting-edge topic in the field of economics. At the same time, stock price forecasting that supports trading strategies is considered one of the most challenging tasks. Therefore, this study analyzes and extracts news media data, expert comments, social opinion data, and pandemic text data using natural language processing, and then combines the data with a deep learning model to forecast future stock price patterns based on historical stock prices. An interval constraint-based trading strategy is constructed. Using data from several typical stocks in the Chinese stock market during the COVID-19 period, the empirical studies and trading simulations show, first, that the sentiment composite index and the deep learning model can improve the accuracy of stock price forecasting. Second, the interval constraint-based trading strategy based on the proposed approach can effectively enhance returns and thus, can assist investors in decision-making. [ABSTRACT FROM AUTHOR]

As the second-largest oil producer and natural gas exporter, Russia's war with Ukraine has severely impacted the energy market. To what extent has the war influenced crude oil prices, and has it altered the long-term dynamics of oil prices? An objective analysis of the effects of the Russia–Ukraine war on the crude oil market can assist relevant entities in developing both short-term emergency strategies and long-term response plans. This study establishes an analytical framework of the event analysis method based on multiresolution causality testing (EMC). The results of the multiresolution causality testing reveal a significant one-way causality between the Russia–Ukraine war and crude oil prices. Afterward, using the event analysis based on variational mode decomposition (VMD), from October 1, 2021, to August 25, 2022, as the event window, we found that the war and its chain events caused the West Texas Intermediate (WTI) crude oil prices to increase by $37.14, a 52.33% surge, and the Brent crude oil price to rise by $41.49, a 56.33% increase. During the event window, the Russia–Ukraine war can account for 70.72% and 73.62% of the fluctuation in WTI and Brent crude oil prices, respectively. Furthermore, the war amplified oil price volatility and fundamentally altered the trend of crude oil prices. Consequently, this study proposes four recommendations: the establishment of an emergency management mechanism for the oil market, the diversification of oil and gas imports by energy-importing countries, the steady advancement of energy transformation, and the judicious use of financial instruments by enterprises to hedge risks. [ABSTRACT FROM AUTHOR]

To seek more business opportunities, cross-market retailers pursue horizontal joint promotion (HJP) to promote their products together. It is important to determine the factors that make cross-market retailers pursue HJP and how HJP affects the retailers' optimal decisions. We address such issues in the context of a shopping mall in which two cross-market retailers pursue HJP with the possible involvement of the shopping mall. We develop game-theoretic models to study whether the shopping mall should provide consumers with coupons that they can obtain from the retailer in the source market and consume at the retailer in the target market. We find that when coupons are offered to consumers, the retailer in the source market has a higher price and will pay more for HJP, but has a smaller demand and a lower profit than the retailer in the target market. Furthermore, when the effect of the coupon is relatively large, both retailers prefer the coupon as they can have higher prices, demands, and profits, and their promotional strategies change with the denomination and effect of the coupon. Conversely, both retailers would reduce investments in HJP because the coupon may bring them lower profits. [ABSTRACT FROM AUTHOR]

We examine the impact of upper (lower) market volatility and skewness risks on stock returns. Our results show that market volatility and skewness risks have no significant effect on future stock returns. However, when separately considering call and put options, we find a significantly negative relation between innovations in upper market volatility (skewness) extracted from call options and subsequent stock returns. Moreover, the results remain significant after controlling for other known factors included in the factor models or a battery of firm-level characteristics. Our research shows that call and put options contain different information, and are differently priced in the stock market. This study can help explain the inconsistent results of the recent papers on asset pricing about market volatility and skewness. [ABSTRACT FROM AUTHOR]

Consumers' reference price effects (RPE) impact market pricing transactions and play a vital role in enterprise pricing decisions. Meanwhile, due to consumers' widespread concern about environmental and ecological issues, more enterprises are taking part in the activity of corporate social responsibility (CSR). Motivated by CSR practices, we examine social work donations (SWD) as a CSR activity. Given practical complexities, we used the profit maximization principle and game theory to focus on a two-echelon supply chain consisting of one manufacturer and one retailer taking part in CSR activity under RPE, where the manufacturer takes part in SWD as CSR practice and collects used products from customers. Five models are developed to investigate the influence of reference price and CSR on remanufacturing supply chain decisions; in specific, the high parameter of reference price benefits the supply chain members' profits, but too high of investment efforts in CSR might hurt the supply chain members. In addition, under the decentralized system, giving appropriate government subsidies can reduce profit losses when RPE exists. Finally, we propose a two-part tariff (TPT) contract to coordinate the decentralized CSR remanufacturing supply chain. Our research can be directly applied to remanufacturing supply chains under RPE in CSR environments. [ABSTRACT FROM AUTHOR]

Tourism managers and practitioners rely on accurate demand forecasting and well-informed management guidance. Given the pandemic's consequences on tourism, future analysis in the during-epidemic era is urgently needed. This study aims to achieve three goals combining the utilization of decomposition algorithms and deep learning models: 1) to investigate the changes in tourism demand according to seasonal fluctuations of various frequencies, 2) to improve modelling accuracy in tourism demand forecasting during non-crisis periods and in the peri-COVID-19 era, and 3) to analyze tourism demand evolution in the peri-Covid-19 era. The volume of domestic tourism in Hawaii is used as sample data for demonstration and validation. The empirical findings demonstrate that the framework provided in this study has excellent interpretability and forecasting accuracy, surpasses all benchmark models in terms of error calculation and statistical tests and can provide further insights into peri-Covid-19 demand analysis and management. [ABSTRACT FROM AUTHOR]

The security of credit card fraud detection (CCFD) models based on machine learning is important but rarely considered in the existing research. To this end, we propose a black-box attack-based security evaluation framework for CCFD models. Under this framework, the semisupervised learning technique and transfer-based black-box attack are combined to construct two versions of a semisupervised transfer black-box attack algorithm. Moreover, we introduce a new nonlinear optimization model to generate the adversarial examples against CCFD models and a security evaluation index to quantitatively evaluate the security of them. Computing experiments on two real data sets demonstrate that, facing the adversarial examples generated by the proposed attack algorithms, all six supervised models considered largely lose their ability to identify the fraudulent transactions, whereas the two unsupervised models are less affected. This indicates that the CCFD models based on supervised machine learning may possess substantial security risks. In addition, the evaluation results for the security of the models generate important managerial implications that help banks reasonably evaluate and enhance the model security. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This work was supported in part by the National Natural Science Foundation of China [Grants 72171160 and 71988101], Key Program of National Natural Science Foundation of China and Quebec Research Foundation (NSFC-FRQ) Joint Project [Grant 7191101304], Key Program of NSFC-FRQSC Joint Project [Grant 72061127002], Excellent Youth Foundation of Sichuan Province [Grant 2020JDJQ0021], and National Leading Talent Cultivation Project of Sichuan University [Grant SKSYL2021-03]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.1297) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2021.0076) at (http://dx.doi.org/10.5281/zenodo.7631457). [ABSTRACT FROM AUTHOR]

This paper explores the optimization for the integrated vehicle routing of package collection and delivery in rural areas, based on the coverage idea and customer self-pickup strategy. The purpose is to optimize package collection and delivery in rural areas with the scattered and small-scale demand for the express service. An integrated vehicle routing model for rural package collection and delivery is established with regard to the radius of customer self-pickup, via taking the sum of operation cost, transportation cost, time penalty cost and carbon emission cost as the optimization goal. A two-stage algorithm based on the improved k-means clustering algorithm and genetic algorithm is designed to solve the model. Ziyuan county of Guangxi province is taken for typical example. The simulation results show that the optimization model can raise vehicle loading rate and service coverage rate, while reducing cost. A rise in the customer's self-pickup radius and the number of packages collected and delivered can decrease the unit collection and delivery cost, and it is found that carbon emissions have little effects on the optimization of vehicle routing from the perspective of cost. [ABSTRACT FROM AUTHOR]

This paper investigates optimal decisions for private banking development in China under two innovative organizational structures—the big retail mode (BRM) and the independent development mode (IDM). Under the BRM, the retail and private banking divisions form a cooperative relationship wherein the former transfers high-net-worth customers to the latter. In addition, retail banking receives a share of private banking revenues. We investigate the optimal revenue-sharing ratio between the two divisions and the optimal effort by private banking to serve transferred customers within the cooperative relationship. The analytical results show that as the private banking division becomes more developed, the optimal revenue-sharing ratio decreases, and the private banking division's optimal effort to serve transferred customers decreases because it puts more effort into acquiring new customers. Under the IDM, the two divisions form a competitive relationship since they compete to acquire customers independently. We investigate customer acquisition efforts in this interdivisional competition. Optimal customer acquisition efforts by both divisions increase in potential assets and rates of return. This paper contributes to the literature by (1) analyzing financial innovation by private banks from an organizational perspective; (2) providing an economic analysis for private banking development in China. [ABSTRACT FROM AUTHOR]

Statistical analysis of COVID-19 mortality is challenging due to its non-stationarity and cross-sectional instability. In this paper, the authors introduce a unified method to evaluate the fatality rate of COVID-19 across countries, whose method provides more reliable information for cross-country comparison than the traditional case-fatality rate (CFR). It emerges that the new method, the block-wise case-fatality rate (BCFR), varies for different countries and in different periods. The authors also decompose the COVID-19 fatality data by three factors: 1) The virus infection dynamics over population in different countries, 2) pure distribution and evolution of instantaneous death rate attributed to different individual's physical characteristics such as age and health, and 3) individual countries' variations affecting interactions between the virus infection and the instantaneous mortality due to individual's physical characteristics. Based on the new three-factor model, the authors obtain six key findings of the COVID-19 fatality rate. Our study suggests that, on average, the estimated instantaneous fatality rate contributes about 57.0% to the global BCFR while the time-varying weight contributes about 41.5% in December 2020. The country-specific contribution of instantaneous fatality rate is significantly higher than that of the time-varying weight. Besides, the country-specific characteristics in demographical, social, and economic aspects would affect the relative severity of the disease. [ABSTRACT FROM AUTHOR]

The need to make more accurate grain demand (GD) forecasting has become a major topic in the current international grain security discussion. Our research aims to improve short-term GD prediction by establishing a multi-factor model that integrates the key factors: shifts in dietary structures, population size and age structure, urbanization, food waste, and the impact of COVID-19. These factors were not considered simultaneously in previous research. To illustrate the model, we projected China's annual GDP from 2022 to 2025. We calibrated key parameters such as conversion coefficients from animal foods to feed grain, standard person consumption ratios, and population size using the latest surveys and statistical data that were either out of date or missing in previous research. Results indicate that if the change in diets continued at the rate as observed during 2013–2019 (scenario 1), China's GD is projected to be 629.35 million tons in 2022 and 658.16 million tons in 2025. However, if diets shift to align with the recommendations in the Dietary Guideline for Chinese Residents 2022 (scenario 2), GD would be lower by 5.9–11.1% annually compared to scenario 1. A reduction in feed grain accounts for 68% of this change. Furthermore, for every 1 percentage point increase in the population adopting a balanced diet, GD would fall by 0.44–0.73 million tons annually during that period. Overlooking changes in the population age structure could lead to an overprediction of annual GDP by 3.8% from 2022 to 2025. With an aging population, China's GD would fall slightly, and adopting a balanced diet would not lead to an increase in GD but would have positive impacts on human health and the environment. Our sensitivity analysis indicated that reducing food waste, particularly cereal, livestock, and poultry waste, would have significant effects on reducing GD, offsetting the higher demand due to rising urbanization and higher incomes. These results underscore the significance of simultaneous consideration of multiple factors, particularly the dietary structure and demographic composition, resulting in a more accurate prediction of GD. Our findings should be useful for policymakers concerning grain security, health, and environmental protection. [ABSTRACT FROM AUTHOR]

Daily tourism demand forecasting can provide important implications for the tourism industry. However, there exist limitations in applying traditional methods to forecast daily tourism demand because of the complex seasonal patterns and holiday effects. In this study, we introduce FB Prophet and apply it to the forecasting of daily tourism demand in the Jiuzhai Valley National Park and Macao from Mainland China. The decomposition result of FB Prophet shows its ability to handle the influence of seasonal patterns and holiday effects. The forecasting results show that considering seasonal patterns, holiday effects, and other predictors can significantly improve the forecasting performance, and FB Prophet outperforms other methods. [ABSTRACT FROM AUTHOR]

Effective and timely forecasting of daily tourism volume is an important topic for tourism practitioners and researchers, which can reduce waste and promote the sustainable development of tourism. Several studies are based on the decomposition-ensemble model to forecast the time series of high volatility in tourism volume, but ignore different forecasting methods suitable for different subseries. This study provides an adaptive decomposition-ensemble hybrid forecasting approach. Firstly, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to effectively decompose the original time series into multiple relatively easy subseries, which reduces the complexity of the data. Secondly, sample entropy calculates the complexity of a sequence, and then adopts the elbow rule to adaptively divide them into different complex sets. Finally, multi-kernel extreme learning machine (KELM) models are used to forecast the components of different sets and integrate them. This hybrid approach makes full use of the advantages of different models, which enables effective use of data. The empirical results demonstrate that the approach can both produce results that are close to the actual values and be utilized as a strategy for forecasting daily tourism volume. [ABSTRACT FROM AUTHOR]

Strict carbon emission regulations are set with respect to countries' territorial seas or shipping activities in exclusive economic zones to meet their climate change commitment under the Paris Agreement. However, no shipping policies on carbon mitigation are proposed for the world's high seas regions, which results in carbon intensive shipping activities. In this paper, we propose a Geographic-based Emission Estimation Model (GEEM) to estimate shipping GHG emission patterns on high seas regions. The results indicate that annual emissions of carbon dioxide equivalent (CO2-e) in shipping on the high seas reached 211.60 million metric tonnes in 2019, accounting for about one-third of all shipping emissions globally and exceeding annual GHG emissions of countries such as Spain. The average emission from shipping activities on the high seas is growing at approximately 7.26% per year, which far surpasses the growth rate of global shipping emission at 2.23%. We propose implementation of policies on each high seas region with respect to the main emission driver identified from our results. Our policy evaluation results show that carbon mitigation policies could reduce emissons by 25.46 and 54.36 million tonnes CO2-e in the primary intervention stage and overall intervention stage, respectively, with 12.09% and 25.81% reduction rates in comparison to the 2019 annual GHG emissions in high seas shipping. [ABSTRACT FROM AUTHOR]

Tourism volume forecasting is the hot topic in tourism management, and deep learning techniques as the promising tool are becoming popular for capturing the characteristics of tourism volume data, which is reflected in two aspects: data dimension reduction (i.e., stacked autoencoders [SAE]) and model forecasting (i.e., bi‐directional gated recurrent unit neural network [Bi‐GRU]). With Hong Kong inbound arrivals as a case, this study has empirically verified that deep learning techniques can improve forecasting accuracy. Furthermore, the proposed approach (i.e., SAE‐Bi‐GRU) is significantly superior to benchmark models (i.e., PCA‐Bi‐GRU with Baidu index and Google trends). [ABSTRACT FROM AUTHOR]

Existing research has shown that combination can effectively improve tourism forecasting accuracy compared with single model. However, the model uncertainty and structural instability in combination for out-of-sample tourism forecasting may influence the forecasting performance. This paper proposes a novel forecast combination approach based on time-varying jackknife model averaging (TVJMA), which can more efficiently handle structural changes and nonstationary trends in tourism data. Using Hong Kong tourism demand from five major tourism source regions as an empirical study, we investigate whether our proposed nonparametric TVJMA-based approach can improve tourism forecasting accuracy further. Empirical results show that the proposed TVJMA-based approach outperforms other competitors including single model and three combination methods in most cases. Findings indicate the outstanding performance of our method is robust to various forecasting horizons and different estimation periods. [ABSTRACT FROM AUTHOR]

Based on first-hand data from 290 small and micro firms in China, [11] illuminate the surge of credit constraints and associated financial risks facing small and micro enterprises amid the COVID-19 pandemic. From a Chinese cultural cognition of crisis management, [9], [10]) offer a holistic depiction of how Chinese firms leverage the development of KM capabilities to make timely strategic emergency responses to the pandemic in different stages of development (i.e. before, during and after the crisis). Introduction Since early 2020, the COVID-19 crisis, classified as a global public health emergency (GPHE), has resulted in a series of devastating impacts, such as the breakdown of industries, massive job losses, natural hazards and social precarity on many national economies, as well as the firms operating and the people dwelling within these nations ([3]). Their results indicate that, apart from calamitous outcomes, the COVID-19 pandemic has also propelled firms to learn new knowledge and thereby achieve miraculous success. [Extracted from the article]

A reliable and efficient forecasting system can be used to warn the general public against the increasing PM2.5 concentration. This paper proposes a novel AdaBoost‐ensemble technique based on a hybrid data preprocessing‐analysis strategy, with the following contributions: (i) a new decomposition strategy is proposed based on the hybrid data preprocessing‐analysis strategy, which combines the merits of two popular decomposition algorithms and has been proven to be a promising decomposition strategy; (ii) the long short‐term memory (LSTM), as a powerful deep learning forecasting algorithm, is applied to individually forecast the decomposed components, which can effectively capture the long‐short patterns of complex time series; and (iii) a novel AdaBoost‐LSTM ensemble technique is then developed to integrate the individual forecasting results into the final forecasting results, which provides significant improvement to the forecasting performance. To evaluate the proposed model, a comprehensive and scientific assessment system with several evaluation criteria, comparison models, and experiments is designed. The experimental results indicate that our developed hybrid model considerably surpasses the compared models in terms of forecasting precision and statistical testing and that its excellent forecasting performance can guide in developing effective control measures to decrease environmental contamination and prevent the health issues caused by a high PM2.5 concentration. [ABSTRACT FROM AUTHOR]

The availability of tourism-related big data increases the potential to improve the accuracy of tourism demand forecasting but presents significant challenges for forecasting, including curse of dimensionality and high model complexity. A novel bagging-based multivariate ensemble deep learning approach integrating stacked autoencoder and kernel-based extreme learning machine (B-SAKE) is proposed to address these challenges in this study. By using historical tourist arrival data, economic variable data, and search intensity index (SII) data, we forecast tourist arrivals in Beijing from four countries. The consistent results of multiple schemes suggest that our proposed B-SAKE approach outperforms the benchmark models in terms of level accuracy, directional accuracy, and even statistical significance. Both bagging and stacked autoencoder can effectively alleviate the challenges brought by tourism big data and improve the forecasting performance of the models. The ensemble deep learning model we propose contributes to tourism demand forecasting literature and benefits relevant government officials and tourism practitioners. [ABSTRACT FROM AUTHOR]

Practitioners and policy makers rely on accurate crude oil forecasting to avoid price risks and grasp investment opportunities, but the core of existing predictive models for such prices is based on point-valued inputs and outputs, which may suffer from informational loss of volatility. This paper addresses this issue by proposing a modified threshold autoregressive interval-valued models with interval-valued factors (MTARIX), as extended by Sun et al. [Threshold autoregressive models for interval-valued time series. J. Econom., 2018, 206, 414–446], to analyze and forecast interval-valued crude oil prices. In contrast to point-valued data methods, MTARIX models simultaneously capture nonlinear features in price trend and volatility, and this informational gain can produce more accurate forecasts. Several interval-valued factors and point-valued threshold variables are analyzed, including supply and demand, speculation, stock market, monetary market, technical factor, and search query data. Empirical results suggest that MTARIX models with appropriate threshold variables outperform other competing forecast models (ACIX, CR-SETARX, ARX, and VARX). The findings indicate that oil price range information is more valuable than oil price level information in forecasting crude oil prices. [ABSTRACT FROM AUTHOR]

Business survey, which starts from the microeconomic level, is a widely used short-term forecasting tool in practice. In this study, the authors examine whether foreign trade survey data collected by China's Ministry of Commerce would provide reliable forecasts of China's foreign trade. The research procedure is designed from three perspectives including forecast information test, turning point forecast, and out-of-sample value forecast. First, Granger causality test detects whether survey data lead exports and imports. Second, business cycle analysis, a non-model based method, is performed. The authors construct composite indexes with business survey data to forecast turning points of foreign trade. Third, model-based numerical forecasting methods, including the Autoregressive Integrated Moving Average Model with Exogenous Variables (ARIMAX) and the artificial neural networks (ANNs) models are estimated. Empirical results show that survey data granger cause imports and exports, the leading composite index provides signal for changes of trade cycles, and quantitative models including survey data generate more accurate forecasts than benchmark models. It is concluded that trade survey data has excellent predictive capabilities for imports and exports, which can offer some priorities for government policy-making and enterprise decision making. [ABSTRACT FROM AUTHOR]

Many researchers have examined the relationship between the original equipment manufacturer (OEM) and the third-party remanufacturer (TPR) and found that is mutually beneficial or competitive. This paper aims to study the competitive strategy and production strategy of the OEM and the TPR. The OEM's competitive strategy is to change their competitive intensity by investing in pricing power of new components. For this problem, two different competitive strategies are proposed: Investment strategy and Non-investment strategy. Two models are established based on competitive strategies, and their analytical solutions are obtained by Stackelberg game. Comparing the two competitive strategies found that only when the investment cost and cost of new components both are low, can the OEM adopt Investment strategy. The Investment strategy have a threefold effect on the OEM: increasing profit, reducing cannibalization, and blocking the TPR's entry. It is also found that as the cost of new components increases, the OEM may shift its competitive strategy from Investment to Non-investment. At the moment of competitive strategy shift, the production strategy may change discontinuously. Finally, comparing the environmental effect found that which competitive strategy is environmentally friendly only depend on the discount factor and the environmental advantages of the remanufactured product. [ABSTRACT FROM AUTHOR]

This study investigates granger causal linkages among six Asian emerging stock markets and the US market over the period 2002–2020, taking into account several crisis periods. The pairwise Granger causality tests for investigating the short-run causality show significant bi- and uni-directional causal relationships in those markets and evidence that they have become more internationally integrated after every crisis period. An exception is Bangladesh with almost no significant short-term causal linkages with other markets. For understanding, how the financial linkages amplify volatility spillover effects, we apply the GARCH-M model and find that volatility and return spillovers act very inversely over time. However, market interface is weak before the crisis periods and becomes very strong during the financial crisis and US-China economic policy uncertainty periods. The US market plays a dominant role during the financial crisis and COVID-19 periods. Further analysis using the VAR model shows that a large proportion of the forecast variance of the Asian emerging stock markets is affected by the S&P 500 and that market shock starts to rise notably from the 1 to 10 period. The overall findings could provide important policy implications in the six countries under study regarding hedging, trading strategies, and financial market regulation. [ABSTRACT FROM AUTHOR]

Decomposition methods are extensively used for processing the complex patterns of tourism demand data. Given tourism demand data's intrinsic complexity, it is critical to theoretically understand how different decomposition methods provide solutions. However, a comprehensive comparison of decomposition methods in tourism demand forecasting is still lacking. Hence, this study systematically investigates the forecasting performance of decomposition methods in tourism demand. Nine popular decomposition methods and six forecasting methods are employed, and their forecasting performance is compared. With Hong Kong visitor arrivals from eight major sources as a sample, three main conclusions are obtained from empirical results. First, all the decomposition methods generally outperform benchmark at all horizons, in both the level and directional forecasting. Second, decomposition methods can be divided into four categories based on forecasting accuracy. Finally, variational mode decomposition method is consistently superior to other eight decomposition methods and can provide the best forecasts in all cases. [ABSTRACT FROM AUTHOR]

As the supply of commodities forms essential lifelines for modern society, commodity price fluctuations can significantly impact the operation and sustainable development of macroeconomics, production activities, and people's security and well-being. The commodity trading market also plays a pivotal role in the competition of the international industrial chain and the sustainable development of the industry. The method of bibliometrics was used in this study to trace the development of research on commodity prices, and statistical and co-citation analyses were conducted on selected literature samples. It was found that the research hotspots in this field are concentrated on four aspects: factors influencing commodity prices, the impact of price fluctuations on the macroeconomy, forecasts of commodity prices, and the financialization of commodities. A current commodity price research network centered on oil prices has formed. Future directions in this field, which developed out of oil shock research 40 years ago, can further investigate the impact of factors and the responses that can be made to emergencies on commodity prices, as well as continuing to develop better methods of commodity price forecasting. [ABSTRACT FROM AUTHOR]

In this study, we propose an adaptive multiscale ensemble (AME) learning approach, which consists of variational mode decomposition (VMD) and least square support vector regression (LSSVR) for seasonal and trend forecasting of tourist arrivals. In the formulation of AME learning approach, the original tourist arrival series is decomposed into the trend, seasonal, and remaining volatility components. Then, ARIMA is used to forecast the trend component, SARIMA is used to forecast the seasonal component, and LSSVR is used to forecast the remaining volatility components. The empirical results demonstrate that our proposed AME learning approach can achieve higher forecasting accuracy. [ABSTRACT FROM AUTHOR]

In recent years, Bitcoin has received substantial attention as potentially high-earning investment. However, its volatile price movement exhibits great financial risks. Therefore, how to accurately predict and capture changing trends in the Bitcoin market is of substantial importance to investors and policy makers. However, empirical works in the Bitcoin forecasting and trading support systems are at an early stage. To fill this void, this study proposes a novel data decomposition-based hybrid bidirectional deep-learning model in forecasting the daily price change in the Bitcoin market and conducting algorithmic trading on the market. Two primary steps are involved in our methodology framework, namely, data decomposition for inner factors extraction and bidirectional deep learning for forecasting the Bitcoin price. Results demonstrate that the proposed model outperforms other benchmark models, including econometric models, machine-learning models, and deep-learning models. Furthermore, the proposed model achieved higher investment returns than all benchmark models and the buy-and-hold strategy in a trading simulation. The robustness of the model is verified through multiple forecasting periods and testing intervals. [ABSTRACT FROM AUTHOR]

In recent years, Bitcoin has received substantial attention as potentially high-earning investment. However, its volatile price movement exhibits great financial risks. Therefore, how to accurately predict and capture changing trends in the Bitcoin market is of substantial importance to investors and policy makers. However, empirical works in the Bitcoin forecasting and trading support systems are at an early stage. To fill this void, this study proposes a novel data decomposition-based hybrid bidirectional deep-learning model in forecasting the daily price change in the Bitcoin market and conducting algorithmic trading on the market. Two primary steps are involved in our methodology framework, namely, data decomposition for inner factors extraction and bidirectional deep learning for forecasting the Bitcoin price. Results demonstrate that the proposed model outperforms other benchmark models, including econometric models, machine-learning models, and deep-learning models. Furthermore, the proposed model achieved higher investment returns than all benchmark models and the buy-and-hold strategy in a trading simulation. The robustness of the model is verified through multiple forecasting periods and testing intervals. [ABSTRACT FROM AUTHOR]

The anti-bullwhip effect, coined by Li et al. in 2005 based on the findings in a simulation study, is the contrary effect of the well-known bullwhip effect. Although there is ample empirical evidence that suggests both effects exist, current literature has not yet provided an integrated framework to address how the two effects are related with each other. By extending the classic work of Lee, Padmanabhan, and Whang of 1997 to a multi-stage supply chain, we derive closed-form formula to analytically describe how the two effects originate initially and then evolve over time and space in the supply chain. Our results show both the bullwhip effect and the anti-bullwhip effect can occur when facing different end-customer demands. However, the magnitude of these effects gradually decreases when moving upstream. We also show the impact of long lead-time on increasing the magnitude of information transformation at the next stage and simultaneously decreasing the magnitude at higher stages. These analytical results provide a theoretical explanation to most simulation findings of Li et al.'s 2005 work and can be used by researchers and practitioners to examine the empirical data and design innovate marketing strategies to convert the unwelcome bullwhip effect into the anti-bullwhip effect. [ABSTRACT FROM PUBLISHER]

With unconventional oil and gas booming in commercial development, its inevitable environmental damage has aroused the public's vigilance. To support the regulation improvement and early-warning system building, it is of great need to learn the regular patterns in recurrent violations both for practitioners and governments. In this respect, we utilized the "Oil and Gas Compliance Report" from the Pennsylvania Department of Environmental Protection from 2000 to 2019, a total of 5737 violation records, to dig out the historical violation patterns. Through LDA (Latent Dirichlet Allocation) analysis combined with the decision tree model, our research attained the following conclusions: first, we find that the LDA themes of violations as "Erosion and sediment" and "Water pollution" are critical factors for "Failed" enforcement results. Therefore, policymakers and practitioners should pay more attention to those two types of accidents. Second, it is noted that counties are also one of the essential features that matter the enforcement results. Third, we need to consider the role of economic punishment dialectically, while it is not a significant feature for successful enforcement results. That is to say, a monetary penalty may not necessarily improve the effectiveness of the company's measurements. [ABSTRACT FROM AUTHOR]

Regional trade agreements (RTAs) have been widely adopted to facilitate international trade and cross-border investment and promote economic development. However, ex ante measurements of the environmental effects of RTAs to date have not been well conducted. Here, we estimate the CO2 emissions burdens of the Regional Comprehensive Economic Partnership (RCEP) after evaluating its economic effects. We find that trade among RCEP member countries will increase significantly and economic output will expand with the reduction of regional tariffs. However, the results show that complete tariff elimination among RCEP members would increase the yearly global CO2 emissions from fuel combustion by about 3.1%, doubling the annual average growth rate of global CO2 emissions in the last decade. The emissions in some developing members will surge. In the longer run, the burdens can be lessened to some extent by the technological spillover effects of deeper trade liberalization. We stress that technological advancement and more effective climate policies are urgently required to avoid undermining international efforts to reduce global emissions. The Regional Comprehensive Economic Partnership (RCEP) will come into force in January 2022. Here the authors quantify ex ante economic and environmental effects following RCEP tariff reductions. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to provide better service to hotel customers during the COVID-19 era. Specifically, this study focuses on understanding the changes in hotel customer satisfaction during the epidemic and formulating effective marketing strategies to satisfy and attract guests. Design/methodology/approach: As the first victim of the COVID-19 virus, China's hotel industry has been profoundly affected and customer satisfaction and needs have also changed. Taking 105,635 hotel reviews obtained from Tripadvisor.com in Beijing and Shanghai as samples, this study explores the changes in consumer satisfaction by using text-mining methods. Findings: The results suggest that there are significant differences in overall ratings, spatial distribution and ratings of different traveller types before and after the epidemic. Generally, customers have higher "tolerance" and are more inclined to give higher ratings and pay more attention to hotel prevention and control measures to reduce health risks after the COVID-19. Research limitations/implications: This paper proves the changes in customer satisfaction before and after the COVID-19 at the theoretical level and reveals the changes in customer attention through the topic model and provides a basis for guiding hotel managers to reduce the impact of the COVID-19 crisis. Practical implications: Empirical findings would provide useful insights into tourism management and improve hotel service quality during the COVID-19 epidemic era. Originality/value: This research explores the hotel customer satisfaction in the field of hotel management before COVID-19 and after COVID-19, by using text mining to analyse mandarin online reviews. The results of this study will suggest that the hotel industry should continuously adjust its products and services based on the effective information obtained from customer reviews, so as to realize the activation and revitalization of the hotel industry in the epidemic era. [ABSTRACT FROM AUTHOR]

Purpose: A serious global public health emergency (GPHE) like the COVID-19 aggravates the inequilibrium of medical care and other critical resources between wealthy and poor nations, which, coupled with the collision of cultures, indicates the vital need for developing humanitarian knowledge transcending cultures. Given the scarcity of literature addressing such unprecedent issues, this paper thus proposes new, unconventional viewpoints and future themes at the intersection of knowledge management (KM) and humanitarian inquiry. Design/methodology/approach: This paper is conceptual in nature. The data of the World Bank and the Office for the Coordination of Humanitarian Affairs are analysed to introduce some emerging real impact topics regarding cross-cultural conflicts and humanitarian knowledge in the post-COVID business world. The theoretical foundation was built upon a critical literature review. Findings: This paper synthesizes the perspectives of culture, KM and the humanistic philosophy to distil the core component of cultural intelligence and comparatively and thereby illuminating why cross-cultural metacognition acts as a priori for achieving cosmopolitan humanitarian knowledge. Research limitations/implications: This paper provides profound implications to academics by highlighting the importance to formulating new, inter-disciplinary themes or unorthodox, phenomenon-driven assumptions beyond the traditional KM domain. This paper also offers practitioners and policymakers valuable insights into coping with the growing disparity between high- and low-income countries by showing warning signs of a looming humanitarian crisis associated with a GPHE context. Originality/value: This paper does not aim to claim the birth of a new domain but call for more research on developing a normative theory of humanitarian knowledge as transcendence of cultures. It implies uncharted territories of great interest and potential for the real impact KM community. [ABSTRACT FROM AUTHOR]

This paper studies the estimation of the partially linear panel data models, allowing for cross-sectional dependence through a common factors structure. This semiparametric additive partial linear framework, including both linear and nonlinear additive components, is more flexible compared to linear models, and is preferred to a fully nonparametric regression because of the 'curse of dimensionality'. The consistency and asymptotic normality of the proposed estimators are established for the case where both cross-sectional dimension and temporal dimension go to infinity. The theoretical findings are further supported for small samples via a Monte Carlo study. The results suggest that the proposed method is robust to a wide variety of data generation processes. [ABSTRACT FROM AUTHOR]

In recent years, the crude oil market has entered a new period of development and the core influence factors of crude oil have also been a change. Thus, we develop a new research framework for core influence factors selection and forecasting. Firstly, this paper assesses and selects core influence factors with the elastic-net regularized generalized linear Model (GLMNET), spike-slab lasso method, and Bayesian model average (BMA). Secondly, the new machine learning method long short-term Memory Network (LSTM) is developed for crude oil price forecasting. Then six different forecasting techniques, random walk (RW), autoregressive integrated moving average models (ARMA), elman neural Networks (ENN), ELM Neural Networks (EL), walvet neural networks (WNN) and generalized regression neural network Models (GRNN) were used to forecast the price. Finally, we compare and analyze the different results with root mean squared error (RMSE), mean absolute percentage error (MAPE), directional symmetry (DS). Our empirical results show that the variable selection-LSTM method outperforms the benchmark methods in both level and directional forecasting accuracy. [ABSTRACT FROM AUTHOR]

The increasing attention on Bitcoin since 2013 prompts the issue of possible evidence for a causal relationship between the Bitcoin market and internet attention. Taking the Google search volume index as the measure of internet attention, time-varying Granger causality between the global Bitcoin market and internet attention is examined. Empirical results show a strong Granger causal relationship between internet attention and trading volume. Moreover, they indicate, beginning in early 2018, an even stronger impact of trading volume on internet attention, which is consistent with the rapid increase in Bitcoin users following the 2017 Bitcoin bubble. Although Bitcoin returns are found to strongly affect internet attention, internet attention only occasionally affects Bitcoin returns. Further investigation reveals that interactions between internet attention and returns can be amplified by extreme changes in prices, and internet attention is more likely to lead to returns during Bitcoin bubbles. These empirical findings shed light on cryptocurrency investor attention theory and imply trading strategy in Bitcoin markets. [ABSTRACT FROM AUTHOR]

The COVID‐19 outbreak has been one of the world's most severe challenges since World War II, which not only reflected in the observable economic depression, but also in emotional damage that is scarcely underscored. This paper estimates the effect of the epidemic on happiness of Chinese residents by capturing the emotions conveyed through massive social media, combined with city‐level epidemic data. We confirm the significant negative impact of the outbreak on life satisfaction, with an extra 1% of cumulative death cases associated with a 0.54% decrease in expressed happiness. Meanwhile, we find that well‐being drops the most in regions with high‐level risk of COVID‐19, and happiness in regions with higher or lower income levels are more vulnerable to the effects of the epidemic, in comparison to the intermediate‐level income regions. Female sentiment exhibits more sensitivity to the epidemic situation than does male sentiment. Furthermore, the timing of major public events also plays a sizable role in determining self‐reported happiness, and our results suggest that pandemic alerts announced by the World Health Organization significantly increased the loss of well‐being, while announcements of city‐unlocking had the opposite impact. The interaction between the outbreak and real‐time expressed happiness provides an important opportunity for reflection on the future governance policies of epidemic containment. Key Points: First, the results indicate significant negative impact of the outbreak on life satisfactionSecond, we find that well‐being drops the most in regions with high‐level risk of COVID‐19Female sentiment exhibits more sensitivity to the epidemic situation than does male sentiment [ABSTRACT FROM AUTHOR]