Decision Support Systems最新文献_第3页

Expectancy as a critical factor of IT adoption for learning toward a successful BMD scholar model implementation in a digital divide context 期望是在数字鸿沟背景下成功实现BMD学者模型的关键因素

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

Decision Support Systems

Pub Date : 2025-12-30 DOI: 10.1016/j.dss.2025.114593

Jean Robert Kala Kamdjoug , Samuel Fosso Wamba , Serge-Lopez Wamba-Taguimdje , Pascal Koko Bashengezi

When introducing new educational systems, governments must consider the expectations of end beneficiaries to ensure alignment between stated objectives and intended outcomes. A notable example is the implementation of the Bachelor–Master–Doctorate (BMD) system in higher education in developing countries. This large-scale reform places particular emphasis on integrating information technologies for learning, commonly referred to as e-learning. However, existing literature on e-learning adoption as a decision support system rarely examines the policies and strategies that shape its integration into educational systems. This study analyzes the factors driving e-learning adoption by higher education institutions in a developing country within the BMD framework. A mixed-methods approach was employed, combining a survey-based study, exploratory qualitative interviews and reports, and a literature review to develop a questionnaire grounded in expectancy–performance theory. Data were analyzed using partial least squares structural equation modeling (PLS-SEM) and fuzzy-set qualitative comparative analysis (fsQCA). The results indicate positive relationships between technological context factors (network speed, network coverage, and device performance), expected academic performance factors (student motivation, course design, learning outcomes, learning assistance, and community-building support), and students' intention to use information technology for learning.

在引入新的教育体系时，政府必须考虑最终受益者的期望，以确保既定目标与预期结果之间的一致性。一个显著的例子是在发展中国家高等教育中实施学士-硕士-博士（BMD）制度。这种大规模的改革特别强调整合学习的信息技术，通常被称为电子学习。然而，现有的关于采用电子学习作为决策支持系统的文献很少研究将其整合到教育系统中的政策和策略。本研究在BMD框架下分析了推动发展中国家高等教育机构采用电子学习的因素。采用混合方法，结合基于调查的研究，探索性质的访谈和报告，以及文献综述来开发基于期望-绩效理论的问卷。采用偏最小二乘结构方程模型（PLS-SEM）和模糊集定性比较分析（fsQCA）对数据进行分析。结果表明，技术环境因素（网络速度、网络覆盖和设备性能）、期望学习成绩因素（学生动机、课程设计、学习成果、学习辅助和社区建设支持）与学生使用信息技术学习意愿之间存在正相关关系。

{"title":"Expectancy as a critical factor of IT adoption for learning toward a successful BMD scholar model implementation in a digital divide context","authors":"Jean Robert Kala Kamdjoug , Samuel Fosso Wamba , Serge-Lopez Wamba-Taguimdje , Pascal Koko Bashengezi","doi":"10.1016/j.dss.2025.114593","DOIUrl":"10.1016/j.dss.2025.114593","url":null,"abstract":"<div><div>When introducing new educational systems, governments must consider the expectations of end beneficiaries to ensure alignment between stated objectives and intended outcomes. A notable example is the implementation of the Bachelor–Master–Doctorate (BMD) system in higher education in developing countries. This large-scale reform places particular emphasis on integrating information technologies for learning, commonly referred to as e-learning. However, existing literature on e-learning adoption as a decision support system rarely examines the policies and strategies that shape its integration into educational systems. This study analyzes the factors driving e-learning adoption by higher education institutions in a developing country within the BMD framework. A mixed-methods approach was employed, combining a survey-based study, exploratory qualitative interviews and reports, and a literature review to develop a questionnaire grounded in expectancy–performance theory. Data were analyzed using partial least squares structural equation modeling (PLS-SEM) and fuzzy-set qualitative comparative analysis (fsQCA). The results indicate positive relationships between technological context factors (network speed, network coverage, and device performance), expected academic performance factors (student motivation, course design, learning outcomes, learning assistance, and community-building support), and students' intention to use information technology for learning.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"202 ","pages":"Article 114593"},"PeriodicalIF":6.8,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928264","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

Understanding cyberloafing in video-conferencing-enabled online learning: A resource-based perspective 理解视频会议在线学习中的网络闲逛：基于资源的视角

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

Decision Support Systems

Pub Date : 2025-12-30 DOI: 10.1016/j.dss.2025.114607

Xusen Cheng , Yanyue Ran , Bo Yang , Shuang Zhang , Jose Benitez

Video-conferencing (VC)-enabled online learning has become a norm in schools and institutions. However, the multitasking capabilities of VC often lead users to exhibit cyberloafing behaviors in learning contexts. Despite its prevalence, there is limited understanding of such deviant behaviors in VC-enabled online learning and how to address them. To tackle this gap, we draw on conservation of resources (COR) theory to investigate the evolutionary logic of effort investment behaviors. Using a sequential mixed-methods approach, we first conducted semi-structured interviews, which revealed two constraining resources and one empowering resource of VC in learning contexts. We propose that an individual's consumption of such environmental resources, along with their individual resources, leads to gains in and losses of self-regulated learning (SRL) within VC-enabled online learning, which in turn affect subsequent cyberloafing behaviors. To test our research model and hypotheses, we conducted a survey with 309 participants, followed by a post-survey interview to triangulate the findings. Our study offers valuable insights into the design and implementation of VC in learning contexts to mitigate cyberloafing behaviors, contributing to both theory and practice.

支持视频会议（VC）的在线学习已经成为学校和机构的一种规范。然而，VC的多任务处理能力经常导致用户在学习环境中表现出网络闲逛行为。尽管它很普遍，但人们对风险投资支持的在线学习中的这种越轨行为以及如何解决它们的理解有限。为了解决这一问题，我们利用资源守恒理论来研究努力投资行为的进化逻辑。采用顺序混合方法，我们首先进行了半结构化访谈，揭示了学习环境中风险投资的两个约束资源和一个授权资源。我们认为，个人对这些环境资源的消耗，以及他们的个人资源，导致了在风险投资支持的在线学习中自我调节学习（SRL）的收益和损失，这反过来影响了随后的网络闲逛行为。为了检验我们的研究模型和假设，我们对309名参与者进行了调查，随后进行了调查后的访谈，以三角测量结果。我们的研究为在学习环境中设计和实现风险投资以减轻网络闲逛行为提供了有价值的见解，对理论和实践都有贡献。

{"title":"Understanding cyberloafing in video-conferencing-enabled online learning: A resource-based perspective","authors":"Xusen Cheng , Yanyue Ran , Bo Yang , Shuang Zhang , Jose Benitez","doi":"10.1016/j.dss.2025.114607","DOIUrl":"10.1016/j.dss.2025.114607","url":null,"abstract":"<div><div>Video-conferencing (VC)-enabled online learning has become a norm in schools and institutions. However, the multitasking capabilities of VC often lead users to exhibit cyberloafing behaviors in learning contexts. Despite its prevalence, there is limited understanding of such deviant behaviors in VC-enabled online learning and how to address them. To tackle this gap, we draw on conservation of resources (COR) theory to investigate the evolutionary logic of effort investment behaviors. Using a sequential mixed-methods approach, we first conducted semi-structured interviews, which revealed two constraining resources and one empowering resource of VC in learning contexts. We propose that an individual's consumption of such environmental resources, along with their individual resources, leads to gains in and losses of self-regulated learning (SRL) within VC-enabled online learning, which in turn affect subsequent cyberloafing behaviors. To test our research model and hypotheses, we conducted a survey with 309 participants, followed by a post-survey interview to triangulate the findings. Our study offers valuable insights into the design and implementation of VC in learning contexts to mitigate cyberloafing behaviors, contributing to both theory and practice.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"202 ","pages":"Article 114607"},"PeriodicalIF":6.8,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928266","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

Brand crisis and recovery in livestream commerce: A psychological contract violation theory perspective 直播商业中的品牌危机与复苏：一个心理契约违约理论的视角

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

Decision Support Systems

Pub Date : 2025-12-27 DOI: 10.1016/j.dss.2025.114597

Jiaqi Liu , Xiang Gong , Zhenxin Xiao , Xiaoxiao Liu , Matthew K.O. Lee , Hongwei Wang

Brand streamer crisis (BSC) is a growing concern in livestream commerce due to its accidental, adverse, and uncontrollable consequences. Drawing on psychological contract violation (PCV) theory, we examine the effect of BSC and its recovery strategies on brand performance. In study 1, we conducted a natural experiment with a synthetic difference-in-differences (SDID) model and found that BSC reduces product sales (i.e., financial performance) and follower increments (i.e., relational performance). In Study 2, we performed an observational study with an interrupted time series (ITS) analysis and revealed that the defensive recovery strategy has positive effects on product sales and follower increments. Additionally, the offensive recovery strategy has a positive effect on product sales, while it has a nonsignificant effect on follower increments. Our study contributes to the literature by developing a PCV perspective of brand crisis and offers effective recovery strategies for practitioners in livestream commerce.

品牌主播危机（Brand streamer crisis，简称BSC）由于其偶然性、不利性和不可控的后果，在直播商业中日益受到关注。运用心理契约违约理论，研究平衡记分卡及其恢复策略对品牌绩效的影响。在研究1中，我们使用合成差异中差异（SDID）模型进行了自然实验，发现平衡计分卡降低了产品销售（即财务绩效）和追随者增量（即关系绩效）。在研究2中，我们使用中断时间序列（ITS）分析进行了观察性研究，发现防御性恢复策略对产品销售和追随者增量有积极影响。此外，进攻性恢复策略对产品销售有正向影响，而对追随者增量的影响不显著。我们的研究通过发展品牌危机的PCV视角为文献做出了贡献，并为直播商业从业者提供了有效的恢复策略。

引用次数: 0

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

Decision Support Systems

Pub Date : 2025-12-27 DOI: 10.1016/j.dss.2025.114599

Hongke Zhao , Zhichen Xiang , Likang Wu , Yanhong Guo

Recommendation systems are pivotal in personalizing user experiences across e-commerce platforms. Yet, they often suffer from inherent biases, such as popularity bias. Popularity bias refers to the tendency of recommendation systems to favor overrepresented items, leading to homogenized suggestions that limit diversity and fail to address the needs of users with unique or less common preferences. While large language models (LLMs) promise to enhance recommendation quality through semantic understanding, they struggle with biased data and insufficient collaborative knowledge. To address these challenges, we propose Causal-Enhanced LLM-based Debiased Recommender System (CLD-Rec), a novel two-stage framework that synergizes causal inference and LLMs to mitigate biases and improve recommendation robustness. In the first stage, causal reasoning identifies and eliminates biases (e.g., popularity bias) from user–item interactions, thereby generating debiased collaborative knowledge. In the second stage, this knowledge is integrated with LLMs; by leveraging the latter’s robust language comprehension capabilities, the system generates personalized recommendations that not only align with user preferences but also ensure fairness. Experimental results show that CLD-Rec consistently outperforms state-of-the-art models across multiple datasets, including Games, Toys, and Sports. Additionally, CLD-Rec demonstrates superior fairness by effectively mitigating popularity bias, leading to more balanced and diverse recommendations.

推荐系统是跨电子商务平台个性化用户体验的关键。然而，他们经常受到固有偏见的影响，比如受欢迎程度偏见。流行偏差是指推荐系统倾向于支持代表性过高的项目，导致同质化的建议，限制了多样性，无法满足具有独特或不太常见偏好的用户的需求。虽然大型语言模型（llm）承诺通过语义理解来提高推荐质量，但它们与有偏见的数据和协作知识不足作斗争。为了解决这些挑战，我们提出了基于因果增强的llm的去偏见推荐系统（CLD-Rec），这是一个新的两阶段框架，可以协同因果推理和llm来减轻偏见并提高推荐的鲁棒性。在第一阶段，因果推理从用户-物品交互中识别并消除偏见（例如，流行偏见），从而产生无偏见的协作知识。在第二阶段，这些知识与法学硕士相结合；通过利用后者强大的语言理解能力，系统生成个性化的推荐，不仅符合用户偏好，而且确保公平性。实验结果表明，CLD-Rec在多个数据集（包括游戏、玩具和体育）上始终优于最先进的模型。此外，CLD-Rec通过有效地减轻人气偏见，展示了卓越的公平性，从而导致更平衡和多样化的推荐。

{"title":"Beyond popularity bias in e-commerce: Aligning collaborative knowledge with large language models via causal intervention for robust recommendations","authors":"Hongke Zhao , Zhichen Xiang , Likang Wu , Yanhong Guo","doi":"10.1016/j.dss.2025.114599","DOIUrl":"10.1016/j.dss.2025.114599","url":null,"abstract":"<div><div>Recommendation systems are pivotal in personalizing user experiences across e-commerce platforms. Yet, they often suffer from inherent biases, such as popularity bias. Popularity bias refers to the tendency of recommendation systems to favor overrepresented items, leading to homogenized suggestions that limit diversity and fail to address the needs of users with unique or less common preferences. While large language models (LLMs) promise to enhance recommendation quality through semantic understanding, they struggle with biased data and insufficient collaborative knowledge. To address these challenges, we propose <strong>Causal-Enhanced LLM-based Debiased Recommender System (CLD-Rec)</strong>, a novel two-stage framework that synergizes causal inference and LLMs to mitigate biases and improve recommendation robustness. In the first stage, causal reasoning identifies and eliminates biases (e.g., popularity bias) from user–item interactions, thereby generating debiased collaborative knowledge. In the second stage, this knowledge is integrated with LLMs; by leveraging the latter’s robust language comprehension capabilities, the system generates personalized recommendations that not only align with user preferences but also ensure fairness. Experimental results show that CLD-Rec consistently outperforms state-of-the-art models across multiple datasets, including Games, Toys, and Sports. Additionally, CLD-Rec demonstrates superior fairness by effectively mitigating popularity bias, leading to more balanced and diverse recommendations.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"202 ","pages":"Article 114599"},"PeriodicalIF":6.8,"publicationDate":"2025-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845032","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

Hierarchy-team appointment implementation and physician service productivity: The moderating role of individual and team characteristics 层级团队预约执行与医师服务生产力：个人与团队特质的调节作用

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

Decision Support Systems

Pub Date : 2025-12-26 DOI: 10.1016/j.dss.2025.114598

Hang Xie , Ji Wu , Doris Chenguang Wu , Xiaomei Zeng

The uneven distribution of patient flow among physicians—marked by overburdened specialists and underutilized junior practitioners—perpetuates systemic inefficiencies in outpatient healthcare systems. This study examines the impact of Hierarchical Team Appointment (HTA) system, an innovative appointment scheduling function that probabilistically allocates patients across tiers, on individual physician's patient-volume-based productivity (PVBP). While prior research focuses on individual physicians' adoption of digital channels, the role of team-based systems like HTA in enhancing PVBP through operational efficiency remains underexplored. In this study, we examine the impact of HTA implementation on individual physician's PVBP, mediated by improvements in efficiency. We also explore how this impact varies across specialties, teams and physicians. Using a quasi-experimental design, we analyzed data from 201 physicians at a leading ophthalmology specialty hospital in China, tracking their weekly HTA engagement. Our findings reveal that HTA participation significantly boosts physician PVBP, particularly for junior physicians and in less complexity specialties. Moreover, HTA mitigates patient flow disparities (6.6 %) between team members. The HTA implementation demonstrates potential for managing patient flow and improving physician PVBP, offering valuable insights for healthcare decision support.

病人流动在医生之间的不均匀分布——以负担过重的专科医生和未充分利用的初级医生为标志——使门诊医疗系统的系统性效率低下。本研究考察了分层团队预约（HTA）系统的影响，这是一种创新的预约调度功能，可以跨层概率地分配患者，对个体医生的基于患者量的生产力（PVBP）。虽然先前的研究主要集中在个体医生对数字渠道的采用上，但基于团队的系统（如HTA）在通过操作效率提高PVBP方面的作用仍未得到充分探索。在这项研究中，我们研究了HTA的实施对个体医生的PVBP的影响，通过提高效率来调节。我们还探讨了这种影响在不同专业、团队和医生之间的差异。采用准实验设计，我们分析了来自中国一家领先眼科专科医院的201名医生的数据，跟踪他们每周的HTA参与情况。我们的研究结果表明，HTA的参与显著提高了医生的PVBP，特别是对于初级医生和不太复杂的专业。此外，HTA减轻了团队成员之间的患者流量差异（6.6%）。HTA的实现显示了管理患者流量和改善医生PVBP的潜力，为医疗保健决策支持提供了有价值的见解。

{"title":"Hierarchy-team appointment implementation and physician service productivity: The moderating role of individual and team characteristics","authors":"Hang Xie , Ji Wu , Doris Chenguang Wu , Xiaomei Zeng","doi":"10.1016/j.dss.2025.114598","DOIUrl":"10.1016/j.dss.2025.114598","url":null,"abstract":"<div><div>The uneven distribution of patient flow among physicians—marked by overburdened specialists and underutilized junior practitioners—perpetuates systemic inefficiencies in outpatient healthcare systems. This study examines the impact of Hierarchical Team Appointment (HTA) system, an innovative appointment scheduling function that probabilistically allocates patients across tiers, on individual physician's patient-volume-based productivity (PVBP). While prior research focuses on individual physicians' adoption of digital channels, the role of team-based systems like HTA in enhancing PVBP through operational efficiency remains underexplored. In this study, we examine the impact of HTA implementation on individual physician's PVBP, mediated by improvements in efficiency. We also explore how this impact varies across specialties, teams and physicians. Using a quasi-experimental design, we analyzed data from 201 physicians at a leading ophthalmology specialty hospital in China, tracking their weekly HTA engagement. Our findings reveal that HTA participation significantly boosts physician PVBP, particularly for junior physicians and in less complexity specialties. Moreover, HTA mitigates patient flow disparities (6.6 %) between team members. The HTA implementation demonstrates potential for managing patient flow and improving physician PVBP, offering valuable insights for healthcare decision support.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"202 ","pages":"Article 114598"},"PeriodicalIF":6.8,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845034","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

Does emotional consistency matter? A study of cover image and narrative text in loan-based crowdfunding 情感一致性重要吗？贷款众筹中的封面形象与叙事文本研究

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

Decision Support Systems

Pub Date : 2025-12-26 DOI: 10.1016/j.dss.2025.114596

Haohao Li , Weitao He , Luning Liu , Yuqiang Feng

In multimodal communication environments, facial emotions in images and emotional expressions in narrative text shape viewers' decision-making processes. However, there have been limited systematic investigations into how these two emotional cues affect crowdfunding outcomes. This study proposes a novel theoretical construct regarding image-text emotional consistency and quantifies it by integrating computer vision and text analysis techniques. A theoretical perspective of information processing indicates an inverted U-shaped relationship between image-text emotional consistency and crowdfunding performance. This nonlinear relationship is enhanced when fundraisers are female but weakened as the project risk level increases. An analysis of a large-scale dataset containing 1,588,821 valid crowdfunding projects on the Kiva platform from 2006 to 2023 supports these theoretical expectations. The findings presented herein enrich theoretical knowledge about the effects of multimodal emotional expressions in crowdfunding and provide practical guidance for designing effective crowdfunding campaigns.

在多模态传播环境中，图像中的面部情绪和叙事文本中的情感表达塑造了观众的决策过程。然而，关于这两种情绪线索如何影响众筹结果的系统调查却非常有限。本研究提出了一种新的关于图像-文本情感一致性的理论结构，并通过计算机视觉和文本分析技术对其进行量化。从信息加工的理论角度来看，图文情感一致性与众筹绩效之间存在倒u型关系。当筹资人是女性时，这种非线性关系会增强，但随着项目风险水平的增加，这种非线性关系会减弱。对Kiva平台上从2006年到2023年的1,588,821个有效众筹项目的大规模数据集的分析支持了这些理论预期。本文的研究结果丰富了关于多模态情感表达在众筹中的作用的理论知识，为设计有效的众筹活动提供了实践指导。

{"title":"Does emotional consistency matter? A study of cover image and narrative text in loan-based crowdfunding","authors":"Haohao Li , Weitao He , Luning Liu , Yuqiang Feng","doi":"10.1016/j.dss.2025.114596","DOIUrl":"10.1016/j.dss.2025.114596","url":null,"abstract":"<div><div>In multimodal communication environments, facial emotions in images and emotional expressions in narrative text shape viewers' decision-making processes. However, there have been limited systematic investigations into how these two emotional cues affect crowdfunding outcomes. This study proposes a novel theoretical construct regarding image-text emotional consistency and quantifies it by integrating computer vision and text analysis techniques. A theoretical perspective of information processing indicates an inverted U-shaped relationship between image-text emotional consistency and crowdfunding performance. This nonlinear relationship is enhanced when fundraisers are female but weakened as the project risk level increases. An analysis of a large-scale dataset containing 1,588,821 valid crowdfunding projects on the Kiva platform from 2006 to 2023 supports these theoretical expectations. The findings presented herein enrich theoretical knowledge about the effects of multimodal emotional expressions in crowdfunding and provide practical guidance for designing effective crowdfunding campaigns.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"202 ","pages":"Article 114596"},"PeriodicalIF":6.8,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845033","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

At your fingertips: Do augmented reality gestures reveal product-related emotion? 触手可及：增强现实手势是否揭示了与产品相关的情感？

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

Decision Support Systems

Pub Date : 2025-12-23 DOI: 10.1016/j.dss.2025.114595

Pratik Tarafdar , Alvin Chung Man Leung , Wei Thoo Yue , Indranil Bose

Advances in immersive technologies give online retailers an opportunity to integrate augmented reality (AR) experiences for their customers. With AR, product presentations shift from static images to interactive virtual experiences. This interaction allows online retailers to identify product-related emotions through affective computing. In mobile AR, customers use touch gestures for virtual interaction. Drawing from theories of immersive media and affective computing, we hypothesize that touch movements and pressure in AR-based mobile applications relate to positive emotions during product interactions. We conducted an observational study in a controlled laboratory setting to test our hypotheses and found that these variables can predict emotional responses. To ensure robustness, we applied explainable AI methods, including Shapley Additive Explanations (SHAP), to interpret the contribution of each touch gesture. We found that specific gestures, including the number of pan movements, the average time for pinch movements, touch pressure, and the number of rotate movements, strongly predict positive emotional responses, highlighting the importance of haptic engagement in immersive shopping experiences. These findings have important theoretical and practical implications. We explain how touch behavior can predict product-related emotions and demonstrate how online retailers can implement emotion analytics in AR shopping applications.

沉浸式技术的进步让在线零售商有机会为他们的客户整合增强现实（AR）体验。有了AR，产品展示从静态图像转变为交互式虚拟体验。这种互动允许在线零售商通过情感计算来识别与产品相关的情感。在移动增强现实中，客户使用触摸手势进行虚拟交互。根据沉浸式媒体和情感计算理论，我们假设基于ar的移动应用程序中的触摸运动和压力与产品交互过程中的积极情绪有关。我们在一个受控的实验室环境中进行了一项观察性研究，以检验我们的假设，发现这些变量可以预测情绪反应。为了确保鲁棒性，我们应用了可解释的人工智能方法，包括Shapley加性解释（SHAP），来解释每个触摸手势的贡献。我们发现，特定的手势，包括平移动作的次数、按压动作的平均时间、触摸压力和旋转动作的次数，强烈地预测了积极的情绪反应，强调了触觉参与在沉浸式购物体验中的重要性。这些发现具有重要的理论和实践意义。我们解释了触摸行为如何预测与产品相关的情感，并展示了在线零售商如何在AR购物应用程序中实现情感分析。

{"title":"At your fingertips: Do augmented reality gestures reveal product-related emotion?","authors":"Pratik Tarafdar , Alvin Chung Man Leung , Wei Thoo Yue , Indranil Bose","doi":"10.1016/j.dss.2025.114595","DOIUrl":"10.1016/j.dss.2025.114595","url":null,"abstract":"<div><div>Advances in immersive technologies give online retailers an opportunity to integrate augmented reality (AR) experiences for their customers. With AR, product presentations shift from static images to interactive virtual experiences. This interaction allows online retailers to identify product-related emotions through affective computing. In mobile AR, customers use touch gestures for virtual interaction. Drawing from theories of immersive media and affective computing, we hypothesize that touch movements and pressure in AR-based mobile applications relate to positive emotions during product interactions. We conducted an observational study in a controlled laboratory setting to test our hypotheses and found that these variables can predict emotional responses. To ensure robustness, we applied explainable AI methods, including Shapley Additive Explanations (SHAP), to interpret the contribution of each touch gesture. We found that specific gestures, including the number of pan movements, the average time for pinch movements, touch pressure, and the number of rotate movements, strongly predict positive emotional responses, highlighting the importance of haptic engagement in immersive shopping experiences. These findings have important theoretical and practical implications. We explain how touch behavior can predict product-related emotions and demonstrate how online retailers can implement emotion analytics in AR shopping applications.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"202 ","pages":"Article 114595"},"PeriodicalIF":6.8,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145822796","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

The effects of tactile kinesics function in live chat systems: The role of interaction comfort and social presence 实时聊天系统中触觉动力学功能的影响：交互舒适和社交存在的作用

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

Decision Support Systems

Pub Date : 2025-12-11 DOI: 10.1016/j.dss.2025.114589

Xixian Peng , Yating Yu , Qiuyu Hu , Xinwei Wang , Lei Wang

Live chat systems have become a critical tool for customer engagement in today's digital business landscape, particularly with the rise of AI-enabled chatbots. This research explores the effective use of a novel sensory feature—tactile kinesics—in live chat systems. Grounded in the S-O-R framework, we investigate how the implementation of tactile kinesics in live chat systems influences satisfaction through social presence and interaction comfort, while also examining potential boundary conditions. To achieve this, we conducted three experimental studies. Study 1 reveals that tactile kinesics in live chat systems benefit human agents but not chatbots in business-oriented contexts. Study 2 shows that tactile kinesics enhance satisfaction with chatbots when the interaction context is perceived as social-oriented. Study 3 demonstrated that using business-related tactile kinesics (e.g., handshake) increases satisfaction with chatbots in business-oriented contexts. Overall, our research contributes to the existing literature by identifying the generally positive effects of tactile kinesics in live chat systems and highlighting the crucial mediating role of interaction comfort.

在当今的数字商业环境中，实时聊天系统已成为客户参与的关键工具，特别是随着人工智能聊天机器人的兴起。本研究探讨了在实时聊天系统中有效使用一种新的感官特征——触觉动力学。在S-O-R框架的基础上，我们研究了实时聊天系统中触觉动力学的实施如何通过社交存在和互动舒适度影响满意度，同时也研究了潜在的边界条件。为此，我们进行了三项实验研究。研究1表明，实时聊天系统中的触觉运动有利于人类代理，而不是面向商业环境的聊天机器人。研究2表明，当互动环境被认为是面向社交的时，触觉运动可以提高对聊天机器人的满意度。研究3表明，在以商业为导向的环境中，使用与商业相关的触觉动作（例如握手）可以提高聊天机器人的满意度。总的来说，我们的研究通过确定触觉动力学在实时聊天系统中的普遍积极影响，并强调交互舒适性的关键中介作用，为现有文献做出了贡献。

{"title":"The effects of tactile kinesics function in live chat systems: The role of interaction comfort and social presence","authors":"Xixian Peng , Yating Yu , Qiuyu Hu , Xinwei Wang , Lei Wang","doi":"10.1016/j.dss.2025.114589","DOIUrl":"10.1016/j.dss.2025.114589","url":null,"abstract":"<div><div>Live chat systems have become a critical tool for customer engagement in today's digital business landscape, particularly with the rise of AI-enabled chatbots. This research explores the effective use of a novel sensory feature—tactile kinesics—in live chat systems. Grounded in the S-O-R framework, we investigate how the implementation of tactile kinesics in live chat systems influences satisfaction through social presence and interaction comfort, while also examining potential boundary conditions. To achieve this, we conducted three experimental studies. Study 1 reveals that tactile kinesics in live chat systems benefit human agents but not chatbots in business-oriented contexts. Study 2 shows that tactile kinesics enhance satisfaction with chatbots when the interaction context is perceived as social-oriented. Study 3 demonstrated that using business-related tactile kinesics (e.g., handshake) increases satisfaction with chatbots in business-oriented contexts. Overall, our research contributes to the existing literature by identifying the generally positive effects of tactile kinesics in live chat systems and highlighting the crucial mediating role of interaction comfort.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"201 ","pages":"Article 114589"},"PeriodicalIF":6.8,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731026","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

Investigating the cross-channel impact of live streaming on retail sales: Evidence from a live streaming e-commerce platform in China 调查直播对零售销售的跨渠道影响：来自中国直播电子商务平台的证据

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

Decision Support Systems

Pub Date : 2025-12-11 DOI: 10.1016/j.dss.2025.114591

Lixia Hu , Jiahui Mo , Qingfei Min , Xin (Robert) Luo

The rapid advancement of live streaming technology has given rise to a novel selling channel, enabling real-time, two-way interaction between retailers and consumers and thereby transforming the operational landscape of e-commerce channels. When considering the adoption of live streaming, retailers must carefully evaluate potential cross-channel spillover effects, as these can significantly impact overall sales performance after implementation. However, the presence, magnitude, and underlying mechanisms of such spillover effects remain poorly understood and warrant further empirical investigation. This research aims to evaluate the overall effect and the cross-channel spillover effects generated by the introduction of live streaming channels, along with their underlying mechanisms. Using a difference-in-differences combined with propensity score matching approach and panel data from a leading e-commerce platform in China. We find that the introduction of live streaming channels significantly enhances overall shop sales performance. Furthermore, it not only enhances the sales performance of live-streamed products on traditional online channel (inward cross-channel spillover effect) but also drives increased sales of non-live-streamed products within the same shop on traditional online channel (outward cross-channel spillover effect). Additionally, the implementation of live streaming channels substantially improves a shop's reputation and expands its fan base, indicating that live streaming plays a key role in building brand equity.

直播技术的快速发展催生了一种全新的销售渠道，使零售商和消费者之间实现了实时、双向的互动，从而改变了电子商务渠道的运营格局。在考虑采用直播时，零售商必须仔细评估潜在的跨渠道溢出效应，因为这些效应在实施后会对整体销售业绩产生重大影响。然而，这种溢出效应的存在、程度和潜在机制仍然知之甚少，需要进一步的实证研究。本研究旨在评估引入直播渠道所产生的整体效应和跨渠道溢出效应，以及其潜在机制。采用差异中的差异结合倾向得分匹配方法和来自中国领先电子商务平台的面板数据。我们发现，直播渠道的引入显著提升了店铺的整体销售业绩。不仅提升了传统线上渠道直播产品的销售业绩（向内跨渠道溢出效应），还带动了传统线上渠道同店非直播产品的销售增长（向外跨渠道溢出效应）。此外，直播渠道的实施大大提高了商店的声誉并扩大了其粉丝基础，这表明直播在建立品牌资产方面发挥了关键作用。

{"title":"Investigating the cross-channel impact of live streaming on retail sales: Evidence from a live streaming e-commerce platform in China","authors":"Lixia Hu , Jiahui Mo , Qingfei Min , Xin (Robert) Luo","doi":"10.1016/j.dss.2025.114591","DOIUrl":"10.1016/j.dss.2025.114591","url":null,"abstract":"<div><div>The rapid advancement of live streaming technology has given rise to a novel selling channel, enabling real-time, two-way interaction between retailers and consumers and thereby transforming the operational landscape of e-commerce channels. When considering the adoption of live streaming, retailers must carefully evaluate potential cross-channel spillover effects, as these can significantly impact overall sales performance after implementation. However, the presence, magnitude, and underlying mechanisms of such spillover effects remain poorly understood and warrant further empirical investigation. This research aims to evaluate the overall effect and the cross-channel spillover effects generated by the introduction of live streaming channels, along with their underlying mechanisms. Using a difference-in-differences combined with propensity score matching approach and panel data from a leading e-commerce platform in China. We find that the introduction of live streaming channels significantly enhances overall shop sales performance. Furthermore, it not only enhances the sales performance of live-streamed products on traditional online channel (inward cross-channel spillover effect) but also drives increased sales of non-live-streamed products within the same shop on traditional online channel (outward cross-channel spillover effect). Additionally, the implementation of live streaming channels substantially improves a shop's reputation and expands its fan base, indicating that live streaming plays a key role in building brand equity.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"201 ","pages":"Article 114591"},"PeriodicalIF":6.8,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145731910","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

Effects of AI reviews on consumers' purchase intention: Influence of product category, review breadth, and consumer review volume AI评论对消费者购买意愿的影响：产品类别、评论广度、消费者评论量的影响

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

Decision Support Systems

Pub Date : 2025-12-10 DOI: 10.1016/j.dss.2025.114590

Xinyao Yu , David Jingjun Xu , Kai Li

AI reviews, defined as product reviews generated by artificial intelligence, represent a novel application of AIGC in e-commerce. This study investigates how AI reviews influence consumers' purchase intention, considering the roles of product category, review breadth, and consumer review volume. Results show that AI reviews significantly increase purchase intention for search products but have no effect on experience products. Moreover, consumer review volume strengthens the effect of AI reviews for search products but weakens it for experience products. In addition, an inverted U-shaped relationship is identified between the breadth of AI reviews and consumers' purchase intention for experience products. These findings highlight the context-dependent effectiveness of AI reviews and extend the literature on AI-generated content, while offering practical implications for e-commerce platforms seeking to leverage AI reviews strategically.

人工智能评论是由人工智能生成的产品评论，是人工智能在电子商务中的一种新应用。本研究考察了人工智能评论如何影响消费者的购买意愿，考虑了产品类别、评论广度和消费者评论量的作用。结果表明，人工智能评论显著增加了搜索类产品的购买意愿，但对体验类产品没有影响。此外，消费者评论量增强了AI评论对搜索产品的影响，但削弱了AI评论对体验产品的影响。此外，人工智能评论的广度与消费者对体验产品的购买意愿之间存在倒u型关系。这些发现突出了人工智能评论的上下文依赖有效性，并扩展了人工智能生成内容的文献，同时为寻求战略性地利用人工智能评论的电子商务平台提供了实际意义。

引用次数: 0