Data Science and Intelligent Management

As chatbots are increasingly deployed to address service failures, understanding their role in facilitating consumer forgiveness has become essential. Several studies have compared consumers’ reactions to service recovery efforts conducted by a human versus a chatbot. Through three scenario-based experiments (total N = 1875) with Chinese participants, our study examines the interaction between service recovery agents (chatbot vs. human), types of consumer loss (utilitarian vs. symbolic), and service failure severity (low vs. high) in influencing consumer forgiveness. The results reveal that in cases of symbolic loss, consumers perceive humans—rather than chatbots—as more capable of providing emotional support during service recovery, thus promoting forgiveness more effectively. However, this discrepancy diminishes in the case of utilitarian loss. Our findings further suggest that the combined effect of service recovery agents and consumer loss on forgiveness is moderated by service failure severity. In the case of low-severity failures, recovery services provided by humans (vs. chatbots) are more effective in fostering forgiveness for consumers experiencing symbolic losses. However, for high-severity failures, regardless of the type of loss, consumers exhibit a higher level of forgiveness toward recovery services provided by humans. This research offers the following practical implications for managers dealing with service failures: strategic escalation to human agents is recommended for symbolic losses or high-severity failures, but chatbots represent a cost-efficient solution for utilitarian losses in low-severity scenarios. Full article

With the significant increase in users’ privacy awareness and strict regulatory response, user privacy protection faces a dilemma between platform operational flexibility and commercial potential. The personal data use authorization has become an important mechanism influencing platform data transactions and government regulation, thereby shaping the development trajectory of the data trading market. Previous literature has yet to fully elucidate the complex interactions and evolutionary equilibrium strategies among the parties involved in data transactions. This study builds an evolutionary game model involving three parties—users, platforms, and the government—to explore the evolutionary equilibrium of users’ personal data use authorization strategy, platforms’ data trading strategy, and the government’s regulatory strategy. The findings reveal that: (1) User authorization does not always promote platform data transactions. Under the personal data use authorization mechanism, user authorization facilitates platform data transactions only when either the data transaction price is low and the value of user behavioral data exceeds a certain threshold, or the data transaction price is high and the value of user behavioral data falls within a specific range. (2) User authorization is not a sufficient condition for the government to impose strict regulatory measures on platform data transactions. When the regulatory cost is low, the government’s strict regulatory strategy is influenced by both the data transaction price and the value of user behavioral data. Specifically, under low-price–medium-value or high-price–high-value conditions, the government tends to strictly regulate platform data transactions when users do not authorize the use of personal data. Conversely, under low-price–high-value or high-price–medium-value conditions, the government is more inclined to enforce strict regulation when users authorize the use of personal data. This study contributes to evaluating the role of the personal data use authorization mechanism, offering valuable insights to platforms and the government on data transactions and regulation. Full article

As the aging society progresses, it is particularly important to strengthen the sharing of silver economy data to promote the development of the silver economy. This paper focuses on analyzing the mechanism by which digital platforms promote silver economy data sharing and constructs an evolutionary game model that includes government departments, digital platforms, enterprises, and elderly people. On this basis, the stability of the strategies of each subject in the system is analyzed, and the influence of key parameters is also discussed. The simulation draws the following conclusions. Firstly, initial strategy proportions significantly influence evolutionary directions. Higher initial proactive participation increases the probability of convergence to the optimal state. Secondly, digital platforms are driven by government regulation intensity, user complaint probabilities, and reputational losses. Increasing fines and user complaint probabilities incentivize platforms to offer high-quality protection. Thirdly, government departments can initially incentivize enterprises and elderly people to participate in data sharing through subsidies and tax incentives and build a long-term driving mechanism by improving regulatory mechanisms and enhancing digital literacy among the elderly people. The research results can serve as a reference for government departments to promote data sharing in the silver economy. Full article

Background: The digitization of health records was expected to improve data quality and accessibility, yet incompleteness remains a widespread challenge that undermines clinical care, interoperability, and downstream analytics. Problem: Evidence shows that missing and under-recorded elements in electronic health records (EHRs) are largely driven by process gaps across patients, providers, technology, and policy—not solely by technical limitations. Objective: This perspective integrates conceptual foundations of incompleteness, synthesizes cross-country evidence, and examines process-level drivers and consequences, with an emphasis on how missingness propagates bias in AI and machine learning systems. Contribution: We present a unifying taxonomy, highlight complementary approaches (e.g., Record Strength Score, distributional testing, and workflow studies), and we propose a pragmatic agenda for mitigation through technical, organizational, governance, and patient-centered levers. Conclusions: While EHR incompleteness cannot be fully eliminated, it can be systematically mitigated through standards, workflow redesign, patient engagement, and governance—essential steps toward building safe, equitable, and effective learning health systems. Full article

With the rapid growth of social media platforms, short video advertisements (SVAs) have been a dominant channel for product sales. However, how to design SVAs that effectively drive product sales, especially in relation to previous SVAs and the related product information, remains underexplored. This study investigates how SVA title congruence influences sales performance through the mediating role of sociability. Specifically, we conceptualized video-video title congruence and video-product title congruence as two forms of content congruence and investigated their effects using data collected from Douyin, the leading short video platform. The empirical results with two-way fixed effects show that high video-video title congruence and low video-product title congruence are both associated with higher product sales. Sociability mediates the relationship between title congruence and sales performance. This study also finds that the creation frequency and product brand significantly moderate these relationships. Furthermore, this study develops several checks to ensure the robustness of the research model and findings, including the Heckman two-stage test. These findings provide theoretical insights into content creation strategies and offer practical implications for both creators and platform managers. Full article

In reaction to evolving consumer preferences, prominent platforms, such as Amazon and JD, have progressively established proprietary store brands. However, the problems related to the sourcing of store brands and the disclosure of their quality information remain uncertain. To fill this gap, this paper utilizes game theory to develop a supply chain consisting of a national brand manufacturer, a third-party manufacturer, and a platform, focusing on the platform’s optimal sourcing strategy—determining whether to source its store brand from the national or third-party manufacturer—while also considering its quality disclosure strategy. We then examine how essential elements, specifically the brand spillover effect and the disclosure cost, influence these strategic decisions. Our research reveals that the quality information disclosure of the store brand occurs when the product quality surpasses a predetermined threshold. Additionally, although the elevated disclosure cost consistently diminishes quality disclosure, the impact of the brand spillover effect on quality disclosure is nonlinear. Finally, the platform’s sourcing strategy depends greatly on the brand spillover effect and the disclosure cost. Specifically, when the brand spillover effect is relatively large (small), the platform prefers to source the store brand from the national (third-party) manufacturer; with a moderate brand spillover effect, a higher (lower) disclosure cost encourages the platform to source from the national (third-party) manufacturer. Full article

This paper advances machine learning (ML)-based streamflow prediction by strategically selecting rainfall events, introducing a new loss function, and addressing rainfall forecast uncertainties. Focusing on the Iowa River Basin, we applied the stochastic storm transposition (SST) method to create realistic rainfall events, which were input into a hydrological model to generate corresponding streamflow data for training and testing deterministic and probabilistic ML models. Long short-term memory (LSTM) networks were employed to predict streamflow up to 12 h ahead. An active learning approach was used to identify the most informative rainfall events, reducing data generation effort. Additionally, we introduced a novel asymmetric peak loss function to improve peak streamflow prediction accuracy. Incorporating rainfall forecast uncertainties, our probabilistic LSTM model provided uncertainty quantification for streamflow predictions. Performance evaluation using different metrics improved the accuracy and reliability of our models. These contributions enhance flood forecasting and decision-making while significantly reducing computational time and costs. Full article

With the steady global progress in integrating technology into healthcare delivery, doctors’ behavioral patterns on online healthcare platforms have increasingly become a focal point in the fields of digital health and healthcare service management. Grounded in Job Crafting Theory, this study constructs a proactive crafting index, which captures doctors’ proactive behaviors on the platform across three dimensions: consultation rate, number of consultations, and response speed. We systematically examine the multidimensional impacts of such behaviors on performance outcomes, including online consultation volume, offline service volume, and user evaluation performance. This study collects publicly available records from a major online healthcare platform in China and conducts empirical analysis using the entropy weight method and econometric techniques. The results reveal that there is an optimal level of proactive engagement: moderate proactivity maximizes online consultation volume, while both insufficient and excessive proactivity reduce it. Offline service volume, in contrast, follows a U-shaped relationship, where moderate proactive engagement minimizes offline visits, while too little or too much engagement leads to more offline service needs. These nonlinear patterns highlight the importance of framing doctors’ proactive behavior to optimize both online engagement and offline service. The findings enrich Job Crafting Theory by identifying boundaries in platform-based service environments and provide actionable insights for platform operators to design behavior management and incentive systems tailored to doctors’ professional rank, patient condition, and regional context. Full article

Internet service platforms dynamically charge service prices to satisfy the time-varying service demand by leveraging both full- and part-time service providers. This study developed a dynamic pricing model for a monopolistic service platform under two pricing strategies: unified pricing and differentiated pricing. The model incorporates key factors such as demand fluctuations, initial demand constraints, and service quality. It proved the optimal dynamic pricing scheme aimed at maximizing the platform’s expected revenue and analyzed the equilibrium gap between the two strategies based on the optimal control theory. The results reveal the following: (a) The service quality elasticity coefficient, potential market, and demand fluctuation factor all positively affect the optimal service price under the two types of pricing strategies, whereas service quality has the opposite effect. (b) Regardless of pricing strategy, the initial service demand restriction negatively affects the optimal price of the platform. The gap between the optimal service prices under the two types of pricing strategies narrows as the potential service demand rises when customers are less sensitive to service price. (c) With initial demand restriction, the optimal service price rises over time as long as the service market satisfies specific conditions, but the expected revenue under the two types of pricing strategies evolves in significantly different trajectories. (d) The differentiated pricing strategy can help the platform improve revenue by setting a lower revenue-sharing ratio. Full article

Wine reviews can connect words to flavours; they entwine sensory experiences into vivid stories. This research explores the intersection of artificial intelligence and oenology by using state-of-the-art neural networks to decipher the nuances in wine reviews. For more accurate wine classification and to capture the essence of what matters most to aficionados, we use Hierarchical Attention Networks enhanced with pre-trained embeddings. We also propose an approach to create captivating marketing images using advanced text-to-image generation models, mining a large review corpus for the most important descriptive terms and thus linking textual tasting notes to automatically generated imagery. Compared to more conventional models, our results show that hierarchical attention processes fused with rich linguistic embeddings better reflect the complexities of wine language. In addition to improving the accuracy of wine classification, this method provides consumers with immersive experiences by turning sensory descriptors into striking visual stories. Ultimately, our research helps modernise wine marketing and consumer engagement by merging deep learning with sensory analytics, proving how technology-driven solutions can amplify storytelling and shopping experiences in the digital marketplace. Full article

Identifying frontier interdisciplinary domains is essential for tracking scientific evolution and informing strategic research planning. This study proposes a comprehensive framework that integrates (1) semantic disciplinary classification using a large language model (GPT-3.5-Turbo), (2) quantitative metrics for interdisciplinarity (degree and integration strength) and frontierness (novelty, growth, and impact), and (3) trend prediction using time series models, including Transformer, LSTM, GRU, Random Forest, and Linear Regression. The framework systematically captures both structural and temporal dimensions of emerging research fields. Compared to conventional citation-based or topic modeling approaches, it enhances semantic precision, supports multi-label classification, and enables forward-looking forecasts. Empirical validation shows that the Transformer model achieved the highest predictive performance, outperforming other deep learning and baseline models. As an illustrative example, the framework was applied to synthetic biology, which demonstrated high interdisciplinarity, strong novelty, and growing academic influence. These results underscore the field’s strategic position as a frontier interdisciplinary domain. Beyond this case, the proposed framework is generalizable to other domains and provides a scalable, data-driven solution for dynamic monitoring of emerging interdisciplinary areas. It holds promise for applications in science and technology intelligence, research evaluation, and policy support. Full article

E-commerce growth has reshaped consumer behavior and retail services, driving parcel demand and challenging last-mile logistics. Existing research predominantly relies on survey data and global regression models that overlook intra-urban spatial heterogeneity in shopping behaviors. This study bridges this gap by analyzing e-commerce demand’s spatial distribution from a retail service perspective, identifying key drivers, and evaluating implications for omnichannel strategies and logistics. Utilizing waybill big data, spatial analysis, and multiscale geographically weighted regression, we reveal: (1) High-density e-commerce demand areas are predominantly located in central districts, whereas peripheral regions exhibit statistically lower volumes. The spatial distribution pattern of e-commerce demand aligns with the urban development spatial structure. (2) Factors such as population density and education levels significantly influence e-commerce demand. (3) Convenience stores play a dual role as retail service providers and parcel collection points, reinforcing their importance in shaping consumer accessibility and service efficiency, particularly in underserved urban areas. (4) Supermarkets exert a substitution effect on online shopping by offering immediate product availability, highlighting their role in shaping consumer purchasing preferences and retail service strategies. These findings contribute to retail and consumer services research by demonstrating how spatial e-commerce demand patterns reflect consumer shopping preferences, the role of omnichannel retail strategies, and the competitive dynamics between e-commerce and physical retail formats. Full article

The port logistics service innovation (PLSI) is closely associated with cross-border e-commerce (CBEC) enterprise performance, given that the port, as the spatial carrier and the joint point of goods, information, customs house affairs, etc., is essentially a key node of the CBEC logistics chain. However, the influence mechanism of PLSI on CBEC enterprise performance has still not yet been elaborated by consensus. To fill this gap, this study aims to figure out the effect mechanism integrating the probe into two variables (i.e., information interaction and environmental upgrade) in a moderated mediation model. Specifically, this study collects questionnaire survey data of logistics enterprises and CBEC enterprises in the Ningbo-Zhoushan Port of China by the Bootstrap method in the software SPSS 26.0. The results show the following: (1) PLSI can positively affect the CBEC enterprise performance; (2) information interaction plays an intermediary role between PLSI and CBEC enterprise performance; and (3) environmental upgrade can not only positively regulate the relationship between information interaction and CBEC enterprise performance, but also enhance the mediating role of information interaction with a moderated intermediary effect. Full article

This study explored the impact of network structure on conflict and project value creation. Network density and network centrality are two network structure dimensions. A survey was undertaken among professionals working in Chinese construction projects. A total of 308 surveys were analyzed using the structural equation model. The results revealed that network centrality has a negative impact on project value creation while network density has a positive impact. Network centrality has a negative impact on substantive conflicts but a positive impact on affective conflicts. The link between centrality and project value creation is weakened by substantive conflict but strengthened by affective conflict. This research gives a new direction for construction project governance and project value management. Furthermore, this research validates the constructive role of substantive conflicts, as well as the destructive impact of affective conflicts, thereby adding to the literature on conflict governance. Full article

Understanding the dynamics of public opinion formation in digital environments is crucial for managing technological communications effectively. This study investigates stance interactions and opinion reversal phenomena in technical discourse through analysis of the Manus AI controversy that generated approximately 36,932 social media interactions during March 2025. Employing an integrated methodology combining Large Language Model (LLM)-enhanced stance detection with agent-based modeling (ABM), we reveal distinctive patterns challenging traditional public opinion theories. Our cross-correlation analysis identifies significant lagged interaction effects between skeptical and supportive stances, demonstrating how critical expressions trigger amplified counter-responses rather than inducing silence. Unlike prior conceptualizations of counter-silencing that emphasize ideological resistance or echo chambers, our notion of the “counter-spiral of silence” specifically highlights lagged emotional responses and reactive amplification triggered by minority expressions in digital technical discourse. We delineate its boundary conditions as arising under high emotional salience, asymmetrical expertise, and platform structures that enable real-time feedback. The agent-based simulation reproduces empirical patterns, revealing how emotional contagion and network clustering mechanisms generate “counter-spiral of silence” phenomena where challenges to dominant positions ultimately strengthen rather than weaken those positions. These findings illuminate how cognitive asymmetries between public expectations and industry realities create distinctive discourse patterns in technical contexts, offering insights for managing technology communication and predicting public response trajectories in rapidly evolving digital environments. Full article

This study investigates the spillover effects of physicians’ prosocial behavior, specifically knowledge sharing, on the paid consultations of other physicians within the same specialty and offline hospital. Using data from an online healthcare platform, we apply propensity score matching to explore how the sharing of medical knowledge by physicians influences the consultation outcomes of their colleagues. The results reveal significant positive spillover effects, indicating that prosocial behavior benefits other physicians within the same specialty and healthcare institution, thereby enhancing collaboration within the healthcare ecosystem. The spillover effect is stronger within the same offline hospital’s physicians on the online healthcare platform, suggesting that knowledge sharing has a more localized impact within the same healthcare institution. Furthermore, the study examines heterogeneity across both physician-level characteristics (e.g., popularity, title, price, gender) and contextual factors (e.g., specialty type, hospital level, wait time, regional GDP). The findings show that the magnitude and direction of spillover effects differ by subgroup, shaped by professional visibility, authority, and organizational structure. These insights contribute to the understanding of how prosocial behavior can foster collaboration and benefit healthcare networks beyond individual physicians, offering practical implications for healthcare platforms, administrators, and policymakers. Full article

With the increasing adoption of digital governance and big data analytics, the quality of government hotline data significantly affects urban governance and public service efficiency. However, existing methods for assessing data record standards focus predominantly on structured data, exhibiting notable inadequacies in handling the complexities inherent in unstructured or semi-structured textual hotline records. To address these shortcomings, this study develops a comprehensive scoring method tailored for evaluating multi-dimensional data record standards in government hotline data. By integrating advanced deep learning models, we systematically analyze six evaluation indicators: classification predictability, dispatch accuracy, record correctness, address accuracy, adjacent sentence similarity, and full-text similarity. Empirical analysis reveals a significant positive correlation between improved data record standards and higher work order completion rates, particularly highlighting the crucial role of semantic-related indicators (classification predictability and adjacent sentence similarity). Furthermore, the results indicate that the work order field strengthens the positive impact of data standards on completion rates, whereas variations in departmental data-handling capabilities weaken this relationship. This study addresses existing inadequacies by proposing a novel scoring method emphasizing semantic measures and provides practical recommendations—including standardized language usage, intelligent analytic support, and targeted staff training—to effectively enhance urban governance. Full article

In online medical consultations, patients convey their medical condition through self-disclosure, and the linguistic features of this disclosure, as signals, may significantly impact doctors’ diagnostic behavior and service quality. Based on signaling theory, this paper collects consultation data from a large online medical platform in China, employs text mining and classification techniques to extract relevant variables, and applies econometric models to empirically examine the effect of patients’ self-disclosure linguistic features on the quality of online medical services. The results indicate that the completeness and readability of patients’ self-disclosure have a significant positive impact on the quality of doctors’ services, while the expertise and positive sentiment of the disclosure have a significant negative effect. From the perspective of signaling theory, this study reveals the mechanism through which patients’ self-disclosure linguistic features influence doctors’ online consultation behavior, providing an important theoretical foundation for promoting online doctor–patient interaction and enhancing patient well-being. Full article

Carbon trading has emerged as a critical environmental and economic mechanism for promoting energy conservation and emission reduction among firms in China. Leveraging big data from listed industrial firms participating in carbon trading, this study employs the super-efficiency SBM model and the common frontier model to evaluate firm-level carbon performance. Using carbon performance as a mediating variable, the study investigates the impact of carbon trading on firm value, considering the moderating effects of internal and external governance mechanisms. The findings reveal the following: (1) Carbon trading enhances firm value by improving carbon performance. (2) Internal governance mechanisms strengthen the positive effect of carbon trading on firm value, while government intervention weakens this effect. (3) The value-enhancing effect of carbon trading is more pronounced for firms in China’s central and western regions. (4) Among industrial firms, carbon trading has the strongest impact on the value of manufacturing firms. These results provide valuable insights for policymakers and firms aiming to align environmental and economic objectives through carbon-trading mechanisms. Full article

As a new business model, cross-border e-commerce has become an important way for countries to meet new foreign trade requirements in the Internet economy. The cross-border logistics industry plays a crucial role in supporting cross-border e-commerce. Compared with domestic e-commerce, cross-border logistics faces more challenges. To address the problems in cross-border logistics, this study takes China as an example and constructs a tripartite evolutionary game model to facilitate information collaboration among cross-border e-commerce platforms, domestic logistics enterprises, and foreign logistics enterprises. The collaboration strategies in this tripartite information system are simulated using MATLAB. The study highlights key factors affecting information cooperation, such as standardization levels, risk and payoff distributions, and their implications on collaboration decisions. Specifically, the results show that higher levels of information collaboration standardization promote cooperative strategies among players; the risk associated with information collaboration is the most sensitive factor influencing decision-making within cross-border logistics alliances; and when the payoff distribution coefficient is too high, other members may resist cooperation. Full article

Academic publications from the Web of Science Core Collection on “e-business” and “artificial intelligence” (AI) are investigated to reveal the role of AI, extract latent themes and identify potential research topics. The proposed methodology includes relevant graphical representations (trends, co-occurrence networks, Sankey diagrams), sentiment analyses and latent topics identification. A renewed interest in these publications is evident post-2018, with a sharp increase in publications around 2020 that can be attributed to the COVID-19 pandemic. Chinese institutions dominate the collaboration network in e-business and AI. Keywords such as “business transformation”, “business value” and “e-business strategy” are prominent, contributing significantly to areas like “Operations Research & Management Science”. Additionally, the keyword “e-agribusiness” recently appears connected to “Environmental Sciences & Ecology”, indicating the application of e-business principles in sustainable practices. Although three sentiment analysis methods broadly agree on key trends, such as the rise in positive sentiment over time and the dominance of neutral sentiment, they differ in detail and focus. Custom analysis reveals more pronounced fluctuations, whereas VADER and TextBlob present steadier and more subdued patterns. Four well-balanced topics are identified with a coherence score of 0.66 using Latent Dirichlet Allocation, which is a probabilistic generative model designed to uncover hidden topics in large text corpora: Topic 1 (29.8%) highlights data-driven decision-making in e-business, focusing on AI, information sharing and technology-enabled business processes. Topic 2 (28.1%) explores AI and Machine Learning (ML) in web-based business, emphasizing customer service, innovation and workflow optimization. Topic 3 (23.6%) focuses on analytical methods for decision-making, using data modeling to enhance strategies, processes and sustainability. Topic 4 (18.5%) examines the semantic web, leveraging ontologies and knowledge systems to improve intelligent systems and web platforms. New pathways such as voice assistance, augmented reality and dynamic marketplaces could further enhance e-business strategies. Full article

Online medical consultation has become a crucial channel for patients seeking health support. Based on data from a psychiatric department in a leading online medical consultation platform in China, this study examines two possible types of online self-presentation strategies (positive impression management strategy and blending-in impression management strategy) employed by doctors in three dimensions: informational management, affective management, and image management, and explores their impact on patient selection. Meanwhile, an information integration perspective was incorporated and the interaction effects between impression management strategies taken by doctors and patient reviews expressed by online patients are also explored. Results indicate that the information quantity (representing the informational management dimension) in doctors’ profiles has a negative impact on patient selection (β = −0.142, p < 0.01), while the positive emotion expression (representing affective management) (β = 0.423, p < 0.01) and profile photo (representing image management) (β = 1.098, p < 0.01) positively influence patient selection. Patient reviews related to expertise positively moderate the effect of information quantity in doctors’ introduction on patient selection (β = −0.632, p < 0.05). In contrast, patient reviews concerning attitude (β = −0.882, p < 0.01) and credibility (β = −0.488, p < 0.01) negatively moderate the effect of emotion expression and profile photos on patient selection, respectively. The findings extend the applicability of impression management theory, providing a novel perspective for comprehending the impact of doctors’ self-presentation on patient selection and its interaction effect with patient impressions. Full article