Decision Support Systems最新文献

Re-evaluating causal inference: Bias reduction in confounder-effect modifier scenarios

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-03-13 DOI: 10.1016/j.dss.2025.114435

Xuan Wang , Tamer Oraby , Xi Mao , Geng Sun , Helmut Schneider

{"title":"Re-evaluating causal inference: Bias reduction in confounder-effect modifier scenarios","authors":"Xuan Wang , Tamer Oraby , Xi Mao , Geng Sun , Helmut Schneider","doi":"10.1016/j.dss.2025.114435","DOIUrl":"10.1016/j.dss.2025.114435","url":null,"abstract":"<div><div>Propensity Score Matching (PSM) is a widely used method for estimating causal treatment effects, but its performance can be limited in complex scenarios. This paper examines cases where a confounder also serves as an effect modifier and compares the bias-reduction performance of PSM with Inverse Probability Weighting (IPW). Using the University of California, Berkeley graduate admission data as an illustrative example, we show that PSM can produce biased estimates of the Average Treatment Effect (ATE) in such contexts. Through a simulation study, we demonstrate that PSM generally fails to adequately reduce bias for the ATE when a confounder is also an effect modifier, while IPW yields less biased estimates with lower Mean Squared Error (MSE). To validate these findings in a more real-world setting, we analyse data generated from a well-known matched-pairs experimental study of Mexico's Seguro Popular de Salud (Universal Health Insurance) Program. From this experiment we derive observational data that incorporates confounders and effect modifiers and compare the performance of PSM and IPW estimators. Our results confirm that IPW consistently provides more accurate and reliable estimates of the ATE, with smaller bias, compared to PSM.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"192 ","pages":"Article 114435"},"PeriodicalIF":6.7,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654745","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

Optimal advertising strategy for streaming platforms: Whether to purchase external consumer data

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-03-03 DOI: 10.1016/j.dss.2025.114427

Jiahe Wang , Nan Feng , Haiyang Feng , Minqiang Li

{"title":"Optimal advertising strategy for streaming platforms: Whether to purchase external consumer data","authors":"Jiahe Wang , Nan Feng , Haiyang Feng , Minqiang Li","doi":"10.1016/j.dss.2025.114427","DOIUrl":"10.1016/j.dss.2025.114427","url":null,"abstract":"<div><div>By utilizing consumer behavioral data, targeted ads can enhance the click-through rates (CTRs) but, at the same time, cause consumer privacy concerns. In this paper, we investigate whether a streaming platform should purchase external consumer data to improve ad-targeting levels, whereby it gain revenue from cost-per-mille (CPM) and cost-per-click (CPC) advertising. We explore how advertising intensity and consumer advertising fatigue interactively determine the data purchase decision and the optimal ad-targeting level of the streaming platform. Our findings indicate that the platform with low advertising intensity or high consumer advertising fatigue is more likely to purchase external consumer data because the ad-driven CTRs are low in these cases. An unexpected finding is that the amount of consumer data purchased by the platform increases with the intensity of privacy concern when advertising intensity is low or when both advertising intensity and fatigue level are high. In these scenarios, the privacy invasion effect resulting from purchasing external consumer data is low due to the low ad-driven CTRs. After purchasing consumer data, to compensate for the privacy invasion effect of targeted ads on consumers, the platform should lower the advertising intensity if and only if the advertising fatigue level is low. Furthermore, we demonstrate that if the platform simultaneously decides on advertising intensity and ad-targeting level, purchasing external consumer data results in a Pareto improvement when the organic CTR is low, benefiting both consumers and the streaming platform. Our findings highlight the importance of balancing advertising precision and consumer privacy on a streaming platform.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"192 ","pages":"Article 114427"},"PeriodicalIF":6.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578331","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

Balancing the costs and benefits of resilience-based decision making

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-24 DOI: 10.1016/j.dss.2025.114425

Weimar Ardila-Rueda , Alex Savachkin , Daniel Romero-Rodriguez , Jose Navarro

{"title":"Balancing the costs and benefits of resilience-based decision making","authors":"Weimar Ardila-Rueda , Alex Savachkin , Daniel Romero-Rodriguez , Jose Navarro","doi":"10.1016/j.dss.2025.114425","DOIUrl":"10.1016/j.dss.2025.114425","url":null,"abstract":"<div><div>Most decision models of system resilience use static, deterministic optimization techniques while focusing on resilience assessment. At present, we lack appropriate decision support methodologies and computational tools that can offer dynamic control of resilience and balance the costs of resilience assurance. This paper presents a stochastic dynamic optimization model, based on an infinite horizon Continuous-Time Markov Decision Process, to balance the intervention costs and reduce the total recovery time ensuing a disruption of a social-physical system. We aim to offer a model that can facilitate its application to different disruption scenarios. Our state-space formulation of the recovery process uses discrete performance intervals, whereby actions and resulting rewards/costs are related to investment resources, which govern state transitions. We illustrate the model via a case study based on the 2010 Northern Colombia Dique Canal breach. Our results show that the optimal policy reduced the recovery time and restoration investment by approximately 40% and 10%, respectively, when compared to the efficiency of the government interventions. The proposed model features dynamic control of recovery resources and considers the costs of resilience assurance. The model can inform policymakers of ways to improve system resilience using balanced disruption recovery strategies.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114425"},"PeriodicalIF":6.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143509109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Are helpful reviews indeed helpful? Analyzing the information and economic value of contextual cues in user-generated images

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-23 DOI: 10.1016/j.dss.2025.114426

Youngeui Kim , Yang Wang

{"title":"Are helpful reviews indeed helpful? Analyzing the information and economic value of contextual cues in user-generated images","authors":"Youngeui Kim , Yang Wang","doi":"10.1016/j.dss.2025.114426","DOIUrl":"10.1016/j.dss.2025.114426","url":null,"abstract":"<div><div>When shopping online, customers may find user-generated images (UGIs) where existing buyers share their product experiences in an actual setting. Drawing on the constructivist theory of visual perception, we propose a cognitive inference process in which shoppers utilize the background objects in UGIs that contextualize a product (e.g., a snow-covered mountain implying cold weather) to infer its features (e.g., the warmth of a jacket). As a result, the contextual cues in UGIs play a critical role in facilitating future buyers' purchase decision-making. Our empirical probes using data from an online outdoor gear and clothing retailer confirm this conjecture by demonstrating that product contextualization in UGIs increases a review's perceived helpfulness and improves sales. By contrast, the contextual cues in the review text only assist buyers' purchase decision process when they contextualize product functionality (e.g., the windproof of a coat). Yet, they do not work for aesthetic attributes (e.g., the color of a coat). We leverage an experiment to explore the relevant mechanism. In the sales analysis, we reveal that not all image content considered helpful would positively affect sales. For example, after we account for the contextual cues in the UGI, the mere presence of an image in product reviews does not affect sales. On the other hand, although illustrating product malfunction in a UGI does not increase its helpfulness, such content hurts sales. We offer managerial implications based on the empirical findings for review platforms that aim to assist online shoppers in making informed purchases.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114426"},"PeriodicalIF":6.7,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143520399","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

Is ambiguity always adverse? Empirical evidence from the wireless emergency alerts during the pandemic

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-19 DOI: 10.1016/j.dss.2025.114424

Jaeho Myeong , Yongjin Park , Jae-Hyeon Ahn

引用次数: 0

Metaverse technology in sustainable supply chain management: Experimental findings

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-14 DOI: 10.1016/j.dss.2025.114423

Kiarash Sadeghi R. , Divesh Ojha , Puneet Kaur , Raj V. Mahto , Amandeep Dhir

{"title":"Metaverse technology in sustainable supply chain management: Experimental findings","authors":"Kiarash Sadeghi R. , Divesh Ojha , Puneet Kaur , Raj V. Mahto , Amandeep Dhir","doi":"10.1016/j.dss.2025.114423","DOIUrl":"10.1016/j.dss.2025.114423","url":null,"abstract":"<div><div>The metaverse is a transformative force in supply chain information systems, particularly in the context of decision-making processes focusing on sustainable development goals. Thus, this study examines: <em>How does the metaverse among stakeholders contribute to the supply chain decision-making processes regarding sustainable development goals</em>? This study is among the first to provide empirical data examining the impact of the metaverse on stakeholders' sustainability assessment. Additionally, we examine how the metaverse influences supply chain collaboration and logistics decisions efficiency, particularly concerning their significant environmental implications. Through the lens of the practice-based theory, we test the proposed relationships using empirical data collected through a scenario-based survey. Furthermore, we analyzed tweets containing the keywords “metaverse” and “supply chain” to identify related topics and sentiments regarding the metaverse. The text mining analysis revealed three primary topics: logistics, digitalization, and sustainability. Results from the sentiment analysis indicated a predominantly positive attitude towards the metaverse within supply chains.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114423"},"PeriodicalIF":6.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the impact of free live-streamed medical consultation on patient engagement and patient satisfaction in the multistage online consultation process: A quasi-experimental design

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-12 DOI: 10.1016/j.dss.2025.114422

Haochen Song , Xitong Guo , Tianshi Wu

{"title":"Exploring the impact of free live-streamed medical consultation on patient engagement and patient satisfaction in the multistage online consultation process: A quasi-experimental design","authors":"Haochen Song , Xitong Guo , Tianshi Wu","doi":"10.1016/j.dss.2025.114422","DOIUrl":"10.1016/j.dss.2025.114422","url":null,"abstract":"<div><div>In recent years, many online healthcare communities (OHCs) in China introduced the feature of free live-streamed medical consultations (FLSMC), which allows patients to communicate with physicians and have an interactive consultation for free through live streaming. Despite the rapid growth of FLSMC, little is known about whether FLSMC can bring benefits to patients when they have online consultation needs in the future. Drawing on signaling theory, this study examines the impact of FLSMC on patient engagement and patient satisfaction in the multistage online consultation process. We further explore the moderating effects of physician's owned and earned signals in the pre-consultation stage by integrating social capital theory with signaling theory. We collect a panel data set of 16,151 physicians from a leading OHC in China. Based on the DID method, a quasi-experimental design, and the instrumental variable method, we demonstrate that FLSMC has a positive effect on patient choice, patient messaging, and patient satisfaction. In addition, we find that the physician's title and online rating can positively moderate the effects of FLSMC on patient choice. This study not only sheds light on the literature on online healthcare by identifying the role of signals in the context of FLSMC, but also provides decision support for patients, physicians, and OHC managers.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114422"},"PeriodicalIF":6.7,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429544","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

DECEN: A deep learning model enhanced by depressive emotions for depression detection from social media content

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-10 DOI: 10.1016/j.dss.2025.114421

Zhijun Yan , Fei Peng , Dongsong Zhang

{"title":"DECEN: A deep learning model enhanced by depressive emotions for depression detection from social media content","authors":"Zhijun Yan , Fei Peng , Dongsong Zhang","doi":"10.1016/j.dss.2025.114421","DOIUrl":"10.1016/j.dss.2025.114421","url":null,"abstract":"<div><div>Depression is a serious and recurrent mental illness that significantly affects an individual's life and the society as a whole. Automatic detection of depression is crucial for early intervention and minimizing negative consequences. Existing studies on building deep learning models for automated depression detection have mainly used post-level emotion polarity (i.e., positive and negative emotions) and word embeddings as predictive features. Few have considered depressive emotions (e.g., anhedonia) expressed in those posts, despite that depressive emotions are essential to clinical depression diagnosis. Moreover, existing approaches for depression detection often ignore the relationship between emotions and their context. This study proposes a Depressive Emotion-Context Enhanced Network (DECEN) that consists of a pre-trained depressive emotion recognition module and an emotion-context enhanced representation module to address those limitations. DECEN first integrates semantic and syntactic structure representations of textual content of social media posts to identify depressive emotions conveyed through terms either explicitly or implicitly, rather than general emotion words. Furthermore, we propose an emotion-context enhanced representation method to enhance the role of the context of depressive emotions in depression detection. The evaluation using real social media data demonstrates that DECEN outperforms the state-of-the-art models in depression detection. The results of an ablation experiment also reveal that the proposed depressive emotion recognition and emotion-context enhanced representation modules, the two novel design artifacts, improve model performance. This study contributes to depression diagnostic decisions by introducing a novel method and providing new technical and practical insights for detecting depression from social media content.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114421"},"PeriodicalIF":6.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395755","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 physicians' noncompliance use of AI-aided diagnosis—A mixed-methods approach

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-10 DOI: 10.1016/j.dss.2025.114420

Jiaoyang Li , Xixi Li , Cheng Zhang

{"title":"Understanding physicians' noncompliance use of AI-aided diagnosis—A mixed-methods approach","authors":"Jiaoyang Li , Xixi Li , Cheng Zhang","doi":"10.1016/j.dss.2025.114420","DOIUrl":"10.1016/j.dss.2025.114420","url":null,"abstract":"<div><div>Despite the pervasiveness of artificial intelligence (AI) technologies in the healthcare industry, physicians are reluctant to follow the recommendations suggested by AI-aided diagnostic systems. We conceptualize physicians' noncompliance use of AI-aided diagnostic systems and draw on the technology threat avoidance theory (TTAT) to investigate the phenomenon of interest. Specifically, we leverage a mixed-methods approach to develop and test a comprehensive research model of physicians' noncompliance use of AI under the overarching theory of TTAT. With an exploratory qualitative study by interviewing ten physicians with experience in using AI-aided diagnostic systems, we observe that (1) physicians experience two distinct types of threats imposed by AI, namely AI threats to diagnostic process and outcome, (2) physicians' resistance to AI-aided diagnostic systems is the underlying psychological mechanism that turns their AI threat perceptions into noncompliance usage behavior, and (3) physicians' professional capital serves as an essential boundary condition in understanding the impacts of AI threats on resistance. In a confirmatory quantitative survey with 160 physicians, we find that (1) both AI threats to diagnostic process and outcome arouse physicians' psychological resistance, (2) such resistance to AI-aided diagnosis leads to noncompliance usage behavior, (3) noncompliance use of AI-aided diagnosis decreases physicians' diagnostic performance enhanced by AI, and (4) physicians' professional capital weakens the positive impact of AI threat to diagnostic process on resistance, but strengthens the positive impact of AI threat to diagnostic outcome on resistance. Our research advances the understanding of post-adoption noncompliance use of AI technology and enriches TTAT in health AI use. Our empirical findings offer practical suggestions for implementing and managing AI technology in the healthcare industry.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114420"},"PeriodicalIF":6.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143520356","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

Is seeing the same as doing? An evaluation of vicarious experiences in the metaverse

IF 6.7 1区计算机科学

Decision Support Systems Pub Date : 2025-02-06 DOI: 10.1016/j.dss.2025.114419

Caleb Krieger , Andy Luse , Ghazal Abdolhossein Khani , Rathindra Sarathy

引用次数: 0