Decision Support Systems最新文献_第8页

How does AI-assisted diagnosis decision support systems influence doctors' coping styles and work outcomes? Bright and dark sides of AI in the workplace 人工智能辅助诊断决策支持系统如何影响医生的应对方式和工作成果？人工智能在工作场所的光明面和阴暗面

IF 6.8 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-10-01 Epub Date: 2025-07-28 DOI: 10.1016/j.dss.2025.114512

Zhaohua Deng , Dan Song , Shan Liu

Artificial intelligence (AI), specifically AI-assisted diagnosis decision support systems (DSSs), have been integrated into doctors' work in substituted or complementary ways. From the perspective of doctors, the impact of AI roles on work outcomes is a double-edged sword that may induce both positive and negative consequences and even create ethical issues related to work. However, little is known on why and how the dual effects take place. To address this knowledge gap, we draw on coping theory and explore the roles of AI-assisted diagnosis DSSs in doctors' work meaningfulness and core work capability through their coping style. We employ a sequential mixed-methods design to develop a theoretical framework and test the research model. Results indicate that perceived complementation and substitution for non-core tasks are positively associated with work specialization (bright side), promoting work meaningfulness and core work capability. By contrast, perceived substitution for core tasks is positively associated with a threat to human distinctiveness (dark side), which harms work meaningfulness and core work capability. Our findings contribute to the emerging literature on AI's impact in the doctors' workplace and provide ethical suggestions for practitioners.

人工智能（AI），特别是人工智能辅助诊断决策支持系统（dss），已经以替代或补充的方式融入到医生的工作中。从医生的角度来看，人工智能角色对工作结果的影响是一把双刃剑，可能会产生积极和消极的后果，甚至会产生与工作相关的伦理问题。然而，人们对这种双重效应发生的原因和方式知之甚少。为了解决这一知识缺口，我们借鉴应对理论，通过应对方式探讨人工智能辅助诊断DSSs在医生工作意义和核心工作能力中的作用。我们采用顺序混合方法设计来建立理论框架并检验研究模型。结果表明，对非核心任务的补充和替代感知与工作专业化（积极面）、工作意义和核心工作能力呈正相关。相反，核心任务的感知替代与对人类独特性（黑暗面）的威胁呈正相关，这损害了工作的意义和核心工作能力。我们的研究结果为人工智能对医生工作场所的影响的新兴文献做出了贡献，并为从业者提供了道德建议。

{"title":"How does AI-assisted diagnosis decision support systems influence doctors' coping styles and work outcomes? Bright and dark sides of AI in the workplace","authors":"Zhaohua Deng , Dan Song , Shan Liu","doi":"10.1016/j.dss.2025.114512","DOIUrl":"10.1016/j.dss.2025.114512","url":null,"abstract":"<div><div>Artificial intelligence (AI), specifically AI-assisted diagnosis decision support systems (DSSs), have been integrated into doctors' work in substituted or complementary ways. From the perspective of doctors, the impact of AI roles on work outcomes is a double-edged sword that may induce both positive and negative consequences and even create ethical issues related to work. However, little is known on why and how the dual effects take place. To address this knowledge gap, we draw on coping theory and explore the roles of AI-assisted diagnosis DSSs in doctors' work meaningfulness and core work capability through their coping style. We employ a sequential mixed-methods design to develop a theoretical framework and test the research model. Results indicate that perceived complementation and substitution for non-core tasks are positively associated with work specialization (bright side), promoting work meaningfulness and core work capability. By contrast, perceived substitution for core tasks is positively associated with a threat to human distinctiveness (dark side), which harms work meaningfulness and core work capability. Our findings contribute to the emerging literature on AI's impact in the doctors' workplace and provide ethical suggestions for practitioners.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"197 ","pages":"Article 114512"},"PeriodicalIF":6.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144749732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

How manipulating information affects information diffusion during disasters: The effects of modifying falsehoods versus corrections 在灾难中操纵信息如何影响信息扩散：修改虚假与更正的效果

IF 6.8 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-10-01 Epub Date: 2025-08-13 DOI: 10.1016/j.dss.2025.114523

Kelvin K. King

Information evolves as it is disseminated on social media. However, studies have largely overlooked a major aspect of the diffusion process: how information is modified, the various dimensions of these modifications, and their roles in the diffusion process. To fill these research gaps, we utilize the Information Manipulation Theory (IMT) as a theoretical lens and a unique panel dataset of 71 falsehoods, propagated during five disasters, to investigate how modifying information affects its diffusion. Our exploratory analysis suggests that at least 65 % of the messages shared are half-truths. Although falsehoods had a higher modification rate for the first 700 h, corrections were modified more aggressively and for 100 h longer after that period, owing to competition. Our empirical analysis suggests that modified information, i.e., information that includes unrelated responses such as deflections, self-referents, additional details, and more information, is generally shared more frequently than unmodified information.

Furthermore, for falsehoods, a one-unit increase in these modifications increases diffusion; however, when manner and quantity modifications increase by one unit for corrections, sharing increases by 115.1 % and 102.2 %, respectively. Although relation modifications from corrections cause an over 149 % increase in sharing at the information diffusion introduction stages, they do not occur in the maturity and decline stages, and are counterproductive in the growth stages. We also find that negatively charged corrections stimulate virality more than positive ones.

These findings have important implications for researchers and decision-makers.

信息随着在社交媒体上的传播而演变。然而，研究在很大程度上忽视了传播过程的一个主要方面：信息是如何被修改的，这些修改的各个方面，以及它们在传播过程中的作用。为了填补这些研究空白，我们利用信息操纵理论（IMT）作为理论透镜和在五次灾难中传播的71个虚假信息的独特面板数据集，来研究修改信息如何影响其传播。我们的探索性分析表明，至少65%的分享信息是半真半假的。虽然谎言在前700小时有较高的修改率，但由于竞争，在此之后更正的修改更积极，并且持续时间更长100小时。我们的实证分析表明，修改后的信息，即包含不相关反应的信息，如偏转、自我指涉、附加细节和更多信息，通常比未修改的信息共享得更频繁。此外，对于谎言，这些修改每增加一个单位，就会增加传播；然而，当修正的方式和数量增加一个单位时，共享分别增加115.1%和102.2%。虽然修正带来的关系修正在信息扩散引入阶段会使共享增加149%以上，但在成熟期和衰退期不会发生，在成长阶段会产生反效果。我们还发现，带负电荷的修正比带正电荷的修正更能刺激病毒式传播。这些发现对研究人员和决策者具有重要意义。

{"title":"How manipulating information affects information diffusion during disasters: The effects of modifying falsehoods versus corrections","authors":"Kelvin K. King","doi":"10.1016/j.dss.2025.114523","DOIUrl":"10.1016/j.dss.2025.114523","url":null,"abstract":"<div><div>Information evolves as it is disseminated on social media. However, studies have largely overlooked a major aspect of the diffusion process: how information is modified, the various dimensions of these modifications, and their roles in the diffusion process. To fill these research gaps, we utilize the Information Manipulation Theory (IMT) as a theoretical lens and a unique panel dataset of 71 falsehoods, propagated during five disasters, to investigate how modifying information affects its diffusion. Our exploratory analysis suggests that at least 65 % of the messages shared are half-truths. Although falsehoods had a higher modification rate for the first 700 h, corrections were modified more aggressively and for 100 h longer after that period, owing to competition. Our empirical analysis suggests that modified information, i.e., information that includes unrelated responses such as deflections, self-referents, additional details, and more information, is generally shared more frequently than unmodified information.</div><div>Furthermore, for falsehoods, a one-unit increase in these modifications increases diffusion; however, when <em>manner</em> and <em>quantity</em> modifications increase by one unit for corrections, sharing increases by 115.1 % and 102.2 %, respectively. Although <em>relation</em> modifications from corrections cause an over 149 % increase in sharing at the information diffusion introduction stages, they do not occur in the maturity and decline stages, and are counterproductive in the growth stages. We also find that negatively charged corrections stimulate virality more than positive ones.</div><div>These findings have important implications for researchers and decision-makers.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"197 ","pages":"Article 114523"},"PeriodicalIF":6.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring users' post-adoption use of generative AI: An attitudinal ambivalence perspective 探索用户采用生成式人工智能后的使用：态度矛盾的观点

IF 6.8 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-10-01 Epub Date: 2025-08-05 DOI: 10.1016/j.dss.2025.114521

Jing Zhang , Zhen Shao , Lin Zhang , Jose Benitez

As generative AI (genAI) has advanced, the intricate interplay of its technical potential and ethical perils has become more pronounced, fostering a growing ambivalence in users' attitudes towards genAI technology. Drawing upon the attitudinal ambivalence perspective (i.e., the simultaneous occurrence of positive and negative evaluations of genAI use) and cognitive appraisal theory of emotion, our study proposes and tests an integrative research model to understand how users' attitudinal ambivalence towards genAI technology navigates their negative and positive emotional responses and shapes their post-adoption behaviors. We surveyed 530 genAI users and employed the structural equation modeling approach to test our research model. We find that attitudinal ambivalence is significantly associated with users' extended use and avoidance through the mediation of user trust and fear. Additionally, transparency significantly moderates the effects of attitudinal ambivalence on user trust and fear. Our study advances nature and consequences of attitudinal ambivalence towards genAI and provides insights for practitioners contemplating deploying genAI.

随着生成式人工智能（genAI）的发展，其技术潜力和伦理风险之间错综复杂的相互作用变得更加明显，导致用户对基因人工智能技术的态度日益矛盾。基于态度矛盾观（即对基因人工智能的正面和负面评价同时出现）和情绪认知评价理论，本研究提出并检验了一个综合研究模型，以了解用户对基因人工智能技术的态度矛盾如何引导他们的消极和积极情绪反应，并影响他们的采用后行为。我们调查了530名genAI用户，并采用结构方程建模方法对我们的研究模型进行了测试。研究发现，通过用户信任和恐惧的中介，态度矛盾心理与用户的扩展使用和回避显著相关。此外，透明度显著调节态度矛盾心理对用户信任和恐惧的影响。我们的研究推进了对基因人工智能态度矛盾的本质和后果，并为考虑部署基因人工智能的从业者提供了见解。

{"title":"Exploring users' post-adoption use of generative AI: An attitudinal ambivalence perspective","authors":"Jing Zhang , Zhen Shao , Lin Zhang , Jose Benitez","doi":"10.1016/j.dss.2025.114521","DOIUrl":"10.1016/j.dss.2025.114521","url":null,"abstract":"<div><div>As generative AI (genAI) has advanced, the intricate interplay of its technical potential and ethical perils has become more pronounced, fostering a growing ambivalence in users' attitudes towards genAI technology. Drawing upon the attitudinal ambivalence perspective (i.e., the simultaneous occurrence of positive and negative evaluations of genAI use) and cognitive appraisal theory of emotion, our study proposes and tests an integrative research model to understand how users' attitudinal ambivalence towards genAI technology navigates their negative and positive emotional responses and shapes their post-adoption behaviors. We surveyed 530 genAI users and employed the structural equation modeling approach to test our research model. We find that attitudinal ambivalence is significantly associated with users' extended use and avoidance through the mediation of user trust and fear. Additionally, transparency significantly moderates the effects of attitudinal ambivalence on user trust and fear. Our study advances nature and consequences of attitudinal ambivalence towards genAI and provides insights for practitioners contemplating deploying genAI.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"197 ","pages":"Article 114521"},"PeriodicalIF":6.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144841759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data disclosure strategy: Navigating the balance between privacy and profit in a dynamic system 数据披露策略：动态系统中隐私与利润的平衡

IF 6.8 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-10-01 Epub Date: 2025-08-11 DOI: 10.1016/j.dss.2025.114510

Cheng-Han Wu

Digital platforms play a crucial role in our interconnected society, relying on user-disclosed data to enhance advertising revenue and user experiences and provide free services. While data accumulation benefits both platforms and users, it raises privacy concerns. This study explores the interaction between user data disclosure strategies and profitability for a platform and a developer, considering three strategies: mandatory data disclosure with free-to-use, mandatory disclosure with pay-to-use, and user-selective disclosure, allowing payment without data sharing. We formulate a dynamic optimization problem to capture how user data accumulation evolves and influences firm decisions. This framework also degenerates into a static setting for comparison, allowing us to assess the impact of dynamic evolution. Our findings reveal that while static models favor payment-based strategies, dynamic models entail a transition from a free-to-use model, facilitating early-stage data accumulation, to a selective disclosure model that balances privacy concerns and profitability. These findings offer guidance for managers in developing adaptive data disclosure strategies that optimize profitability while addressing user privacy concerns.

数字平台在我们这个互联的社会中扮演着至关重要的角色，依靠用户披露的数据来提高广告收入和用户体验，并提供免费服务。虽然数据积累对平台和用户都有利，但它引发了隐私问题。本研究探讨了用户数据披露策略与平台和开发商盈利能力之间的相互作用，考虑了三种策略：免费使用的强制性数据披露，付费使用的强制性数据披露，以及用户选择性披露，允许在不共享数据的情况下付费。我们制定了一个动态优化问题来捕捉用户数据积累如何演变和影响公司决策。这个框架也退化为一个静态的比较设置，允许我们评估动态进化的影响。我们的研究结果表明，静态模式有利于基于付费的策略，而动态模式则需要从免费使用模式（促进早期数据积累）过渡到平衡隐私问题和盈利能力的选择性披露模式。这些发现为管理人员开发适应性数据披露策略提供了指导，这些策略可以在解决用户隐私问题的同时优化盈利能力。

{"title":"Data disclosure strategy: Navigating the balance between privacy and profit in a dynamic system","authors":"Cheng-Han Wu","doi":"10.1016/j.dss.2025.114510","DOIUrl":"10.1016/j.dss.2025.114510","url":null,"abstract":"<div><div>Digital platforms play a crucial role in our interconnected society, relying on user-disclosed data to enhance advertising revenue and user experiences and provide free services. While data accumulation benefits both platforms and users, it raises privacy concerns. This study explores the interaction between user data disclosure strategies and profitability for a platform and a developer, considering three strategies: mandatory data disclosure with free-to-use, mandatory disclosure with pay-to-use, and user-selective disclosure, allowing payment without data sharing. We formulate a dynamic optimization problem to capture how user data accumulation evolves and influences firm decisions. This framework also degenerates into a static setting for comparison, allowing us to assess the impact of dynamic evolution. Our findings reveal that while static models favor payment-based strategies, dynamic models entail a transition from a free-to-use model, facilitating early-stage data accumulation, to a selective disclosure model that balances privacy concerns and profitability. These findings offer guidance for managers in developing adaptive data disclosure strategies that optimize profitability while addressing user privacy concerns.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"197 ","pages":"Article 114510"},"PeriodicalIF":6.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144841753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Gamified giving: Contingent effects of leaderboard rankings on donation behavior in online medical crowdfunding 游戏化捐赠：排行榜排名对在线医疗众筹捐赠行为的偶然影响

IF 6.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-09-01 Epub Date: 2025-07-08 DOI: 10.1016/j.dss.2025.114505

Yi Wu , Leping Xiao , Zhongtao Hu , Na Liu , Nan Feng

Online medical crowdfunding has emerged as a vital resource for patients seeking public assistance. As a typical gamification design, leaderboards play a crucial role in boosting users' donation. Grounded in motivational affordance and social influence theories, this study investigates how different leaderboard types and rankings influence donation through the underlying mechanism of sense of self-worth. A 2 (leaderboard ranking: high vs. low) × 2 (leaderboard type: public vs. social) between-subject experiment was conducted to validate our research model. The results reveal that high rankings enhance users' donation intentions by boosting their sense of self-worth. This positive effect is more pronounced in public leaderboards than in social ones. Additionally, donation experience weakens the positive effect of sense of self-worth on donation intention. This study contributes to the decision support systems literatures on online crowdfunding and gamification design with practical implications for fundraising strategies.

在线医疗众筹已成为寻求公共援助的患者的重要资源。作为一种典型的游戏化设计，排行榜在促进用户捐赠方面发挥着至关重要的作用。本研究以动机启示理论和社会影响理论为基础，探讨了不同排行榜类型和排名如何通过自我价值感的潜在机制影响捐赠。为了验证我们的研究模型，我们进行了2（排行榜排名：高vs低）× 2（排行榜类型：公共vs社交）受试者间实验。结果显示，高排名通过提升用户的自我价值感来增强他们的捐赠意愿。这种积极影响在公共排行榜中比在社交排行榜中更为明显。此外，捐赠经历削弱了自我价值感对捐赠意愿的正向作用。本研究对网络众筹和游戏化设计的决策支持系统文献有一定的借鉴意义。

引用次数: 0

An agent-based model to analyze the influence of IS integration and IS assimilation on the adoption dynamics of a green supply chain: The case of regional consolidation centers 基于agent的信息系统整合和信息系统同化对绿色供应链采用动态影响分析模型——以区域整合中心为例

IF 6.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-09-01 Epub Date: 2025-06-30 DOI: 10.1016/j.dss.2025.114501

François de Corbière , Hirotoshi Takeda , Johanna Habib , Frantz Rowe , Daniel Thiel

To improve its economic and environmental performance, Carrefour, a major European retailer, restructured the distribution of logistic flows from its small and medium suppliers by introducing consolidation centers to expand flows and optimize resource sharing. The success of such an innovative supply chain (SC) largely depends on the number of suppliers deciding to adopt it without reverting to the previous SC. This specific context prompted us to propose a multi-agent model to analyze how the success of SC restructuring evolves as a function of delivery costs, information system (IS) integration and assimilation, and institutional pressures. Simulation results show first that, the lower IS integration in both the extant and the new SC, the more firms switch to and stay in the new SC. Second, a high level of IS assimilation in the new SC structure combined with coercive pressures fosters the success of SC restructuring.

为了改善其经济和环境绩效，欧洲主要零售商家乐福通过引入整合中心来扩大流量和优化资源共享，重组了中小型供应商的物流流分布。这种创新供应链（SC）的成功在很大程度上取决于决定采用它而不回到以前的供应链的供应商的数量。这一特定背景促使我们提出一个多智能体模型来分析供应链重组的成功是如何作为交付成本、信息系统（IS）集成和同化以及制度压力的函数演变的。模拟结果表明，首先，在现有和新的供应链中，越低的信息系统整合，越多的公司转向并留在新的供应链中。其次，在新的供应链结构中，高水平的信息系统同化与强制压力相结合，促进了供应链重组的成功。

引用次数: 0

Handling imperfection: A taxonomy for machine learning on data with data quality defects 处理缺陷：一种针对具有数据质量缺陷的数据进行机器学习的分类法

IF 6.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-09-01 Epub Date: 2025-06-16 DOI: 10.1016/j.dss.2025.114493

Michael Hagn, Bernd Heinrich, Thomas Krapf, Alexander Schiller

In recent years, machine learning (ML) has become ubiquitous in sectors including transportation, security, health, and finance to analyze large amounts of data and support decision-making. However, real-world datasets used in ML often exhibit various data quality (DQ) defects that can significantly impair the performance and validity of ML models and thus also the decisions derived from them. Therefore, a plethora of methods across various research strands have been proposed to address DQ defects and mitigate their negative impact on ML-based data analysis and decision support. This has resulted in a fragmented research landscape, where comparisons and classifications of methods dealing with ML on data with DQ defects are very challenging for both researchers and practitioners. Thus, based on a structured design process, we develop and present a taxonomy for this research field. The taxonomy serves as a systematic framework to classify and organize existing research and methods according to relevant dimensions and facilitates future work in this area. Its reliability, understandability, completeness, and usefulness are supported by an evaluation with external researchers and practitioners. Finally, we identify current trends and research gaps and derive challenges and directions for future research.

近年来，机器学习（ML）在交通、安全、健康和金融等领域无处不在，可以分析大量数据并支持决策。然而，机器学习中使用的真实数据集经常表现出各种数据质量（DQ）缺陷，这些缺陷会严重损害机器学习模型的性能和有效性，从而也会损害从中得出的决策。因此，已经提出了跨越各种研究领域的大量方法来解决DQ缺陷，并减轻它们对基于ml的数据分析和决策支持的负面影响。这导致了一个支离破碎的研究领域，其中比较和分类的方法处理ML的数据与DQ缺陷是非常具有挑战性的研究人员和从业者。因此，基于一个结构化的设计过程，我们为这个研究领域开发并提出了一个分类法。该分类法作为一个系统的框架，将现有的研究和方法按照相关的维度进行分类和组织，并有助于今后在这一领域的工作。它的可靠性，可理解性，完整性和有用性是由外部研究人员和实践者的评估支持的。最后，我们确定了当前的趋势和研究差距，并得出了未来研究的挑战和方向。

{"title":"Handling imperfection: A taxonomy for machine learning on data with data quality defects","authors":"Michael Hagn, Bernd Heinrich, Thomas Krapf, Alexander Schiller","doi":"10.1016/j.dss.2025.114493","DOIUrl":"10.1016/j.dss.2025.114493","url":null,"abstract":"<div><div>In recent years, machine learning (ML) has become ubiquitous in sectors including transportation, security, health, and finance to analyze large amounts of data and support decision-making. However, real-world datasets used in ML often exhibit various data quality (DQ) defects that can significantly impair the performance and validity of ML models and thus also the decisions derived from them. Therefore, a plethora of methods across various research strands have been proposed to address DQ defects and mitigate their negative impact on ML-based data analysis and decision support. This has resulted in a fragmented research landscape, where comparisons and classifications of methods dealing with ML on data with DQ defects are very challenging for both researchers and practitioners. Thus, based on a structured design process, we develop and present a taxonomy for this research field. The taxonomy serves as a systematic framework to classify and organize existing research and methods according to relevant dimensions and facilitates future work in this area. Its reliability, understandability, completeness, and usefulness are supported by an evaluation with external researchers and practitioners. Finally, we identify current trends and research gaps and derive challenges and directions for future research.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"196 ","pages":"Article 114493"},"PeriodicalIF":6.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Flight delay dynamics: Unraveling the impact of airport-network-spilled propagation on airline on-time performance 航班延误动力学：揭示机场网络溢出传播对航空公司准点率的影响

IF 6.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-09-01 Epub Date: 2025-07-01 DOI: 10.1016/j.dss.2025.114494

Yi Tan , Yajun Lu , Lu Wang

Flight delay prediction has attracted increasing attention in airline operations. Early identification of potential flight delays is crucial for improving airport scheduling and airline operations while mitigating associated costs. This study investigates the influence of the potential propagation of flight delays throughout the airport network via interconnected flights, a mechanism we term Airport-Network-Spilled Propagation (ANSP). To model the ANSP mechanism, we develop a novel time-dependent, network-based approach that decays the importance of past delays. From this network, we extract a real-time ANSP score for each airport to measure the influence of propagated delays. To evaluate our proposed approach, we employ four state-of-the-art machine learning models using domestic airline on-time performance data from the 30 Large Hub airports in the United States. The results demonstrate that integrating the ANSP score with established features from airline operations literature significantly enhances flight departure delay prediction performance, achieving an increase in AUC of up to 5.49%. Furthermore, we conduct an explainable AI analysis using Shapley additive explanations (SHAP), which reveals that our ANSP score ranks as the most important predictor among all features tested.

航班延误预测在航空公司运营中越来越受到关注。及早发现潜在的航班延误对于改善机场调度和航空公司运营，同时降低相关成本至关重要。本研究探讨了航班延误通过互联航班在整个机场网络中潜在传播的影响，我们称之为机场-网络溢出传播（ANSP）机制。为了对ANSP机制进行建模，我们开发了一种新的基于时间的网络方法，该方法降低了过去延迟的重要性。从这个网络中，我们提取了每个机场的实时ANSP分数，以衡量传播延迟的影响。为了评估我们提出的方法，我们采用了四种最先进的机器学习模型，使用了来自美国30个大型枢纽机场的国内航空公司准点率数据。结果表明，将ANSP得分与航空公司运营文献中已建立的特征相结合，显著提高了航班离港延误预测的性能，AUC提高了5.49%。此外，我们使用Shapley加性解释（SHAP）进行了可解释的人工智能分析，这表明我们的ANSP分数是所有测试特征中最重要的预测因子。

{"title":"Flight delay dynamics: Unraveling the impact of airport-network-spilled propagation on airline on-time performance","authors":"Yi Tan , Yajun Lu , Lu Wang","doi":"10.1016/j.dss.2025.114494","DOIUrl":"10.1016/j.dss.2025.114494","url":null,"abstract":"<div><div>Flight delay prediction has attracted increasing attention in airline operations. Early identification of potential flight delays is crucial for improving airport scheduling and airline operations while mitigating associated costs. This study investigates the influence of the potential propagation of flight delays throughout the airport network via interconnected flights, a mechanism we term Airport-Network-Spilled Propagation (ANSP). To model the ANSP mechanism, we develop a novel time-dependent, network-based approach that decays the importance of past delays. From this network, we extract a real-time ANSP score for each airport to measure the influence of propagated delays. To evaluate our proposed approach, we employ four state-of-the-art machine learning models using domestic airline on-time performance data from the 30 Large Hub airports in the United States. The results demonstrate that integrating the ANSP score with established features from airline operations literature significantly enhances flight departure delay prediction performance, achieving an increase in AUC of up to 5.49%. Furthermore, we conduct an explainable AI analysis using Shapley additive explanations (SHAP), which reveals that our ANSP score ranks as the most important predictor among all features tested.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"196 ","pages":"Article 114494"},"PeriodicalIF":6.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144565839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Knowledge-based Context-aware Group Recommender System for Point of Interest recommendation 基于知识的上下文感知组推荐系统，用于兴趣点推荐

IF 6.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-09-01 Epub Date: 2025-06-18 DOI: 10.1016/j.dss.2025.114485

Nargis Pervin , Abhishek Kulkarni , Ayush Adarsh , Shreya Som

The rise of Location-based Social Networking (LBSN) platforms has transformed the way users explore Points of Interest (POIs), increasingly relying on group-based recommendations. However, recommending POIs to groups presents unique challenges due to conflicting preferences among members. Traditional group recommendation algorithms often prioritize aggregated methods or explicit preference extraction, overlooking latent domain-specific information and the dynamic nature of group decision-making. To address these gaps, we propose a novel Knowledge-based Context-Aware Group Recommender System (KCGRS) designed to support decision-making processes within groups. KCGRS operates in two key stages: first, it utilizes a knowledge graph to learn domain-specific embeddings for both users and POIs, ensuring that implicit preferences and contextual factors are incorporated. In the second stage, these embeddings are enhanced with contextual information using a feed-forward transformer model, allowing for a more nuanced understanding of real-time preferences. The decision-making process is further refined by generating a group embedding, which is computed by applying a weighted aggregate of the context-infused embeddings of individual group members. This approach models group dynamics and decision processes more accurately, ensuring that the final recommendation reflects the collective preferences of the group. Experiments on real-world Yelp data show that KCGRS significantly outperforms five state-of-the-art baselines, delivering up to an average of 14.15% improvement in Hit ratio and a 13.07% increase in NDCG compared to the next best method while also maintaining competitive runtime efficiency. Furthermore, KCGRS demonstrates enhanced diversity and coverage in recommendations, ensuring that POI suggestions cater to a broader range of user preferences while avoiding over-personalization. This balance between accuracy, diversity, and efficiency highlights KCGRS’s effectiveness in supporting group decision-making and its potential to enhance collaborative recommendations in LBSN platforms. Finally, a user study with 144 participants was conducted that resulted in statistically significant levels of user satisfaction and trust in the recommendations, thereby supporting the practical effectiveness of the KCGRS system.

基于位置的社交网络（LBSN）平台的兴起改变了用户探索兴趣点（poi）的方式，越来越依赖于基于群体的推荐。然而，由于成员之间的偏好冲突，向团体推荐poi面临着独特的挑战。传统的群体推荐算法往往优先考虑聚合方法或显式偏好提取，忽略了潜在的特定领域信息和群体决策的动态性。为了解决这些差距，我们提出了一种新的基于知识的上下文感知群体推荐系统（KCGRS），旨在支持群体内的决策过程。KCGRS分为两个关键阶段：首先，它利用知识图来学习用户和poi的特定领域嵌入，确保隐含偏好和上下文因素被纳入其中。在第二阶段，使用前馈变压器模型增强这些嵌入的上下文信息，允许对实时首选项进行更细致的理解。决策过程通过生成组嵌入进一步细化，该组嵌入通过应用单个组成员的上下文注入嵌入的加权聚合来计算。这种方法更准确地模拟了群体动态和决策过程，确保最终的建议反映了群体的集体偏好。在真实Yelp数据上的实验表明，KCGRS显著优于5个最先进的基线，与次优方法相比，命中率平均提高14.15%，NDCG平均提高13.07%，同时保持有竞争力的运行效率。此外，KCGRS在推荐中展示了增强的多样性和覆盖范围，确保POI建议迎合更广泛的用户偏好，同时避免过度个性化。这种准确性、多样性和效率之间的平衡突出了KCGRS在支持群体决策方面的有效性，以及在LBSN平台中增强协作推荐的潜力。最后，对144名参与者进行了一项用户研究，结果显示用户满意度和对建议的信任程度在统计上具有显著水平，从而支持了KCGRS系统的实际有效性。

{"title":"Knowledge-based Context-aware Group Recommender System for Point of Interest recommendation","authors":"Nargis Pervin , Abhishek Kulkarni , Ayush Adarsh , Shreya Som","doi":"10.1016/j.dss.2025.114485","DOIUrl":"10.1016/j.dss.2025.114485","url":null,"abstract":"<div><div>The rise of Location-based Social Networking (LBSN) platforms has transformed the way users explore Points of Interest (POIs), increasingly relying on group-based recommendations. However, recommending POIs to groups presents unique challenges due to conflicting preferences among members. Traditional group recommendation algorithms often prioritize aggregated methods or explicit preference extraction, overlooking latent domain-specific information and the dynamic nature of group decision-making. To address these gaps, we propose a novel Knowledge-based Context-Aware Group Recommender System (KCGRS) designed to support decision-making processes within groups. KCGRS operates in two key stages: first, it utilizes a knowledge graph to learn domain-specific embeddings for both users and POIs, ensuring that implicit preferences and contextual factors are incorporated. In the second stage, these embeddings are enhanced with contextual information using a feed-forward transformer model, allowing for a more nuanced understanding of real-time preferences. The decision-making process is further refined by generating a group embedding, which is computed by applying a weighted aggregate of the context-infused embeddings of individual group members. This approach models group dynamics and decision processes more accurately, ensuring that the final recommendation reflects the collective preferences of the group. Experiments on real-world Yelp data show that KCGRS significantly outperforms five state-of-the-art baselines, delivering up to an average of 14.15% improvement in Hit ratio and a 13.07% increase in NDCG compared to the next best method while also maintaining competitive runtime efficiency. Furthermore, KCGRS demonstrates enhanced diversity and coverage in recommendations, ensuring that POI suggestions cater to a broader range of user preferences while avoiding over-personalization. This balance between accuracy, diversity, and efficiency highlights KCGRS’s effectiveness in supporting group decision-making and its potential to enhance collaborative recommendations in LBSN platforms. Finally, a user study with 144 participants was conducted that resulted in statistically significant levels of user satisfaction and trust in the recommendations, thereby supporting the practical effectiveness of the KCGRS system.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"196 ","pages":"Article 114485"},"PeriodicalIF":6.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact of categorization autonomy on effective use and adoption intentions 分类自主性对有效使用和采用意图的影响

IF 6.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Decision Support Systems

Pub Date : 2025-09-01 Epub Date: 2025-06-25 DOI: 10.1016/j.dss.2025.114499

Arash Saghafi , Poonacha Medappa , Ariton Debrliev

Category tree view is an omnipresent element in graphical user interfaces where it captures information in terms of a hierarchical structure. These categorization trees facilitate human users' cognitive economy and decision-making. While previous research has investigated the utilities of using unstructured data compared to pre-categorized information by business users, the effectiveness of allowing users the autonomy to create their own categorization hierarchies from generic object types remains unexplored. This paper evaluates the benefits of categorization autonomy in terms of search precision, as an objective measure, as well as subjective intentions to use the system. We examined users' interactions with a platform in information seeking tasks with 201 subjects. Our findings indicate that categorization autonomy leads to superior results, both in terms of effective use and behavioral perceptions. We also found that the impact of categorization autonomy is moderated by task flexibility, such that the benefits are more apparent in tasks that necessitate open-ended search approaches. By focusing on how user-driven categorization influences system interaction, our study contributes to the design of decision support systems that are better aligned with users' cognitive structures and task demands.

类别树视图是图形用户界面中无处不在的元素，它根据层次结构捕获信息。这些分类树有利于人类用户的认知经济和决策。虽然以前的研究已经调查了使用非结构化数据与业务用户预分类信息的效用，但允许用户从通用对象类型中自主创建自己的分类层次结构的有效性仍未得到探索。本文从搜索精度（作为一种客观衡量标准）和使用该系统的主观意愿两方面来评估分类自治的好处。我们研究了201个主题的用户在信息搜索任务中与平台的交互。我们的研究结果表明，无论是在有效使用方面还是在行为感知方面，分类自主都能带来更好的结果。我们还发现，分类自主性的影响受到任务灵活性的调节，因此，在需要开放式搜索方法的任务中，其好处更为明显。通过关注用户驱动的分类如何影响系统交互，我们的研究有助于设计更符合用户认知结构和任务需求的决策支持系统。

{"title":"Impact of categorization autonomy on effective use and adoption intentions","authors":"Arash Saghafi , Poonacha Medappa , Ariton Debrliev","doi":"10.1016/j.dss.2025.114499","DOIUrl":"10.1016/j.dss.2025.114499","url":null,"abstract":"<div><div>Category tree view is an omnipresent element in graphical user interfaces where it captures information in terms of a hierarchical structure. These categorization trees facilitate human users' cognitive economy and decision-making. While previous research has investigated the utilities of using unstructured data compared to pre-categorized information by business users, the effectiveness of allowing users the autonomy to create their own categorization hierarchies from generic object types remains unexplored. This paper evaluates the benefits of categorization autonomy in terms of search precision, as an objective measure, as well as subjective intentions to use the system. We examined users' interactions with a platform in information seeking tasks with 201 subjects. Our findings indicate that categorization autonomy leads to superior results, both in terms of effective use and behavioral perceptions. We also found that the impact of categorization autonomy is moderated by task flexibility, such that the benefits are more apparent in tasks that necessitate open-ended search approaches. By focusing on how user-driven categorization influences system interaction, our study contributes to the design of decision support systems that are better aligned with users' cognitive structures and task demands.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"196 ","pages":"Article 114499"},"PeriodicalIF":6.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144503391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0