Decision Support Systems最新文献

英文中文

Integrating direct and indirect views for group recommendation: An inter- and intra-view contrastive learning method

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114380

Xiangyu Li , Xunhua Guo , Guoqing Chen

The growing popularity of online social networking has made it increasingly important to develop group recommender systems (RS) for delivering personalized services to the members of user groups. However, owing to the sparsity of data on group–item interactions (G–I interactions), existing group recommendation methods have concentrated on modeling user–item interactions (U–I interactions), which has limited the validity of the extracted group preferences. We propose a novel inter- and intra-view contrastive learning (I2VC) method for group recommendation, focusing on combining the direct view concerning group–item records and the indirect view concerning user–item records. The proposed method features a contrastive learning mechanism that incorporates two strategies (i.e., inter-view learning and intra-view learning) to overcome challenges in achieving the cross-view matching of the same group and the within-view discrimination among different groups. We empirically evaluate the proposed method using two real-world datasets. The results show that our method is more effective than other group recommendation methods. In addition, our findings show that the I2VC method is capable of boosting the alignment of strongly correlated group embeddings and the dispersion of weakly correlated ones, further demonstrating its effectiveness in view collaboration.

{"title":"Integrating direct and indirect views for group recommendation: An inter- and intra-view contrastive learning method","authors":"Xiangyu Li , Xunhua Guo , Guoqing Chen","doi":"10.1016/j.dss.2024.114380","DOIUrl":"10.1016/j.dss.2024.114380","url":null,"abstract":"<div><div>The growing popularity of online social networking has made it increasingly important to develop group recommender systems (RS) for delivering personalized services to the members of user groups. However, owing to the sparsity of data on group–item interactions (G–I interactions), existing group recommendation methods have concentrated on modeling user–item interactions (U–I interactions), which has limited the validity of the extracted group preferences. We propose a novel inter- and intra-view contrastive learning (I2VC) method for group recommendation, focusing on combining the direct view concerning group–item records and the indirect view concerning user–item records. The proposed method features a contrastive learning mechanism that incorporates two strategies (i.e., inter-view learning and intra-view learning) to overcome challenges in achieving the cross-view matching of the same group and the within-view discrimination among different groups. We empirically evaluate the proposed method using two real-world datasets. The results show that our method is more effective than other group recommendation methods. In addition, our findings show that the I2VC method is capable of boosting the alignment of strongly correlated group embeddings and the dispersion of weakly correlated ones, further demonstrating its effectiveness in view collaboration.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"189 ","pages":"Article 114380"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143170848","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

Realizing desired effects from digitized product affordances: A case study of key inhibiting factors

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114365

Ainara Novales , Martin Mocker , Eric van Heck , Jan Dul

Despite the potential of IoT-enriched digitized products, firms struggle to generate desired impact. We investigate the alignment of actualized digitized product potentials (i.e., affordances) with organizational goals, examining how the emergence of critical inhibiting factors affect the generation of desired effects. We conduct an embedded single case study of four actualized digitized product potentials within a professional equipment manufacturer and explore how the emergence of inhibiting factors prevents the generation of desired effects. Using Necessary Condition Analysis (NCA), six key inhibiting factors are identified. Our findings contribute to affordance theory and digital innovation research in three ways: a) we provide an extended affordance-actualization model that theorizes the process by which emerging key inhibiting factors are addressed via the implementation of (re-)actions to generate desired effects that are aligned with the organizational goals of actualized digitized product potentials, (b) we identify six key inhibiting factors that affect the generation of desired effects and that re-examine the role of data with respect to the “technology” element in affordance theory, and (c) we apply NCA to affordance theory for the first time and show how it can contribute to identifying critical factors during the realization of technology potentials.

{"title":"Realizing desired effects from digitized product affordances: A case study of key inhibiting factors","authors":"Ainara Novales , Martin Mocker , Eric van Heck , Jan Dul","doi":"10.1016/j.dss.2024.114365","DOIUrl":"10.1016/j.dss.2024.114365","url":null,"abstract":"<div><div>Despite the potential of IoT-enriched digitized products, firms struggle to generate desired impact. We investigate the alignment of actualized digitized product potentials (i.e., affordances) with organizational goals, examining how the emergence of critical inhibiting factors affect the generation of desired effects. We conduct an embedded single case study of four actualized digitized product potentials within a professional equipment manufacturer and explore how the emergence of inhibiting factors prevents the generation of desired effects. Using Necessary Condition Analysis (NCA), six key inhibiting factors are identified. Our findings contribute to affordance theory and digital innovation research in three ways: a) we provide an extended affordance-actualization model that theorizes the process by which emerging key inhibiting factors are addressed via the implementation of (re-)actions to generate desired effects that are aligned with the organizational goals of actualized digitized product potentials, (b) we identify six key inhibiting factors that affect the generation of desired effects and that re-examine the role of data with respect to the “technology” element in affordance theory, and (c) we apply NCA to affordance theory for the first time and show how it can contribute to identifying critical factors during the realization of technology potentials.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"189 ","pages":"Article 114365"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169631","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

Time for a change! Uprooting users embedded in the status quo from habitual decision-making

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114371

Xue Sun , Bo Guo , Yufeng Yang , Yu Pan

Introducing the feature of “Buy Again” or “Order Again” is a common practice for online platforms to facilitate consumer repurchases. Although the adoption of these features can cultivate consumers' dependence on focal products and promote habitual purchases, it potentially hinders the promotion of new products and reduces consumer choice diversity. This raises a broader issue of how to inhibit habitual decision-making, rendering exploring the underlying mechanisms for inhibiting habitual decision-making essential, a topic largely overlooked by previous literature. To address this gap, this research explores how decision-related new information, namely Bayesian updating information, influences consumers' repeated decision-making. Utilizing the paradigm of Monty Hall dilemma, the findings show that Bayesian updating information curtails habitual decisions by encouraging consumers to choose alternative options in both scenarios in which the initial choices are self-decided or given by default. Applying the HDDM (hierarchical drift-diffusion model), the results indicate that, in both scenarios, Bayesian updating information reduces consumers' status quo bias, i.e., mitigates their initial preferences for initial choices, and facilitates the accumulation of evidence for changing initial choices. Notably, when the initial choices are self-decided, consumers with Bayesian updating information tend to seek more evidence to make decisions than those without it, while this trend is not observed when the initial choices are given by default. These findings deepen our understanding of online repeated decision-making and provide valuable insights into the design of decision support systems to discourage consumers' habitual decisions and enhance their choice diversity in online shopping.

{"title":"Time for a change! Uprooting users embedded in the status quo from habitual decision-making","authors":"Xue Sun , Bo Guo , Yufeng Yang , Yu Pan","doi":"10.1016/j.dss.2024.114371","DOIUrl":"10.1016/j.dss.2024.114371","url":null,"abstract":"<div><div>Introducing the feature of “Buy Again” or “Order Again” is a common practice for online platforms to facilitate consumer repurchases. Although the adoption of these features can cultivate consumers' dependence on focal products and promote habitual purchases, it potentially hinders the promotion of new products and reduces consumer choice diversity. This raises a broader issue of how to inhibit habitual decision-making, rendering exploring the underlying mechanisms for inhibiting habitual decision-making essential, a topic largely overlooked by previous literature. To address this gap, this research explores how decision-related new information, namely Bayesian updating information, influences consumers' repeated decision-making. Utilizing the paradigm of Monty Hall dilemma, the findings show that Bayesian updating information curtails habitual decisions by encouraging consumers to choose alternative options in both scenarios in which the initial choices are self-decided or given by default. Applying the HDDM (hierarchical drift-diffusion model), the results indicate that, in both scenarios, Bayesian updating information reduces consumers' status quo bias, i.e., mitigates their initial preferences for initial choices, and facilitates the accumulation of evidence for changing initial choices. Notably, when the initial choices are self-decided, consumers with Bayesian updating information tend to seek more evidence to make decisions than those without it, while this trend is not observed when the initial choices are given by default. These findings deepen our understanding of online repeated decision-making and provide valuable insights into the design of decision support systems to discourage consumers' habitual decisions and enhance their choice diversity in online shopping.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"189 ","pages":"Article 114371"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169633","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

Digitalization of the natural sciences: Design science research and computational science

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114368

Veda C. Storey, Richard L. Baskerville

In the natural sciences, many research activities now require the support of digital artifacts. This digitalization of science has led to the need to develop essential, specialized, devices and software. Computational science is a branch of science that especially requires such artifacts. This research examines computational science to identify its challenges and successes in developing and applying digital artifacts as it moves to digital science. We propose that it might be possible and helpful to support digital artifact creation by applying results from research in design science. We are especially motivated by the types of problems encountered in computational science and how they might be supported by design science research methods and evaluation approaches to develop and assess artifacts for important, and complex, real-world problems. In a complementary manner, computational science could provide an area of inquiry for extending design science research into the natural sciences.

引用次数: 0

Unveiling the metaverse: A comparison of multiple environments

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114384

Sumanta Singha , Kiran Pedada , Pradeep Racherla , Srinivas Pingali

The advent of the metaverse is fundamentally altering the relationship dynamics between brands and users. Brands that successfully navigate this new landscape create deeper engagement and foster lasting brand loyalty. Using a multi-method, multi-study approach, we examine the interplay between user characteristics and brand perception in a real metaverse environment called “Universe”, created by a large public sector bank in India. Study 1 involves a qualitative analysis (i.e., focus group discussion) to derive insights for the conceptual model. Study 2 involves quantitative analysis of survey data conducted in three different experimental settings: first-person perspective (1PP), third-person perspective (3PP), and third-person perspective with peer interaction (3PP social). The study reveals that users' social connectedness, technology readiness, and domain literacy positively impact brand perception via two distinct mechanisms: sense of presence and product engagement. Further, our analysis shows that these outcomes vary significantly across the three experimental settings. Whereas product engagement emerges as the dominant mechanism in the 1PP environment, sense of presence emerges as the dominant mechanism in the 3PP social setting. Our study provides several important theoretical and managerial implications for brands, users, and decision science scholars.

{"title":"Unveiling the metaverse: A comparison of multiple environments","authors":"Sumanta Singha , Kiran Pedada , Pradeep Racherla , Srinivas Pingali","doi":"10.1016/j.dss.2024.114384","DOIUrl":"10.1016/j.dss.2024.114384","url":null,"abstract":"<div><div>The advent of the metaverse is fundamentally altering the relationship dynamics between brands and users. Brands that successfully navigate this new landscape create deeper engagement and foster lasting brand loyalty. Using a multi-method, multi-study approach, we examine the interplay between user characteristics and brand perception in a real metaverse environment called “Universe”, created by a large public sector bank in India. Study 1 involves a qualitative analysis (i.e., focus group discussion) to derive insights for the conceptual model. Study 2 involves quantitative analysis of survey data conducted in three different experimental settings: first-person perspective (1PP), third-person perspective (3PP), and third-person perspective with peer interaction (3PP social). The study reveals that users' social connectedness, technology readiness, and domain literacy positively impact brand perception via two distinct mechanisms: sense of presence and product engagement. Further, our analysis shows that these outcomes vary significantly across the three experimental settings. Whereas product engagement emerges as the dominant mechanism in the 1PP environment, sense of presence emerges as the dominant mechanism in the 3PP social setting. Our study provides several important theoretical and managerial implications for brands, users, and decision science scholars.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"189 ","pages":"Article 114384"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143170845","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

Are you caught in the dilemma of metaverse avatars? The impact of individuals' congruity perceptions on paradoxical emotions and actual behaviors

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114387

Xusen Cheng , Shuang Zhang , Jian Mou

As the foundation of the metaverse, three-dimensional avatars are increasingly shaping our personal and professional lives. However, a nuanced reading of avatar literature proposes that avatars can exhibit both positive and negative dimensions, leading to a paradoxical phenomenon. This study aims to conceptualize a holistic framework elucidating the intricate interplay between perceptions, emotions, and actual behaviors to substantiate the salience of paradoxical emotions. Employing a mixed-methods approach comprising think-aloud experiments and interviews (Phase 1), surveys (Phase 2), and follow-up interviews (Phase 3), the study endeavors to develop and validate a model grounded in a three-congruity perspective encompassing self, privacy, and function. Research findings underline that perceived control, social presence, and avatar perception heighten individuals' emotional attachment toward avatars, while social presence mitigates emotional paradoxes. Avatar privacy concern increases emotional paradox without affecting emotional attachment. Additionally, emotional attachment negatively correlates with actual metaverse resistance, whereas emotional paradox positively influences such resistance; conversely, emotional attachment positively correlates with actual metaverse avatar usage. This study extends the existing dual-congruity theory and provides practical implications for metaverse platforms to improve interactive experiences with avatars.

{"title":"Are you caught in the dilemma of metaverse avatars? The impact of individuals' congruity perceptions on paradoxical emotions and actual behaviors","authors":"Xusen Cheng , Shuang Zhang , Jian Mou","doi":"10.1016/j.dss.2024.114387","DOIUrl":"10.1016/j.dss.2024.114387","url":null,"abstract":"<div><div>As the foundation of the metaverse, three-dimensional avatars are increasingly shaping our personal and professional lives. However, a nuanced reading of avatar literature proposes that avatars can exhibit both positive and negative dimensions, leading to a paradoxical phenomenon. This study aims to conceptualize a holistic framework elucidating the intricate interplay between perceptions, emotions, and actual behaviors to substantiate the salience of paradoxical emotions. Employing a mixed-methods approach comprising think-aloud experiments and interviews (Phase 1), surveys (Phase 2), and follow-up interviews (Phase 3), the study endeavors to develop and validate a model grounded in a three-congruity perspective encompassing self, privacy, and function. Research findings underline that perceived control, social presence, and avatar perception heighten individuals' emotional attachment toward avatars, while social presence mitigates emotional paradoxes. Avatar privacy concern increases emotional paradox without affecting emotional attachment. Additionally, emotional attachment negatively correlates with actual metaverse resistance, whereas emotional paradox positively influences such resistance; conversely, emotional attachment positively correlates with actual metaverse avatar usage. This study extends the existing dual-congruity theory and provides practical implications for metaverse platforms to improve interactive experiences with avatars.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"189 ","pages":"Article 114387"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143170847","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

Can earnings conference calls tell more lies? A contrastive multimodal dialogue network for advanced financial statement fraud detection

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

Decision Support Systems

Pub Date : 2025-02-01 DOI: 10.1016/j.dss.2024.114381

Qi Lu , Wei Du , Shaochen Yang , Wei Xu , J. Leon Zhao

Financial statement frauds by listed firms pose significant challenges to public investors and jeopardize the stability of financial markets. Previous studies have identified deceptive verbal and vocal cues from earnings conference calls as indicators of financial statement fraud. However, these studies only extracted managers' verbal and vocal cues separately over the entire call, neglecting the utterance-level fusion between verbal and vocal cues as well as the multi-turn interaction between analysts and managers. To fill this gap, we develop a novel end-to-end contrastive multimodal dialogue network (CMMD) that considers both verbal-vocal fusion and multi-role interactions to uncover hidden deceptive cues in earnings conference calls. The proposed model comprises two core modules, namely, the Multimodal Fusion Learning module and the Dialogue Interaction Learning module. Building on Vrij's verbal-nonverbal complementary mechanisms in deception detection, the designed Multimodal Fusion Learning employs contrastive learning to align verbal and vocal cues and a co-attention mechanism to learn cross-modal interaction. Inspired by the Interpersonal Deception Theory that emphasizes the dynamic interaction process between deceivers and targets, the Dialogue Interaction Learning utilizes a dialogue-aware co-attention mechanism to model multi-turn analyst-manager interaction and uses contrastive learning to improve dialogue representations. Our extensive empirical results show that CMMD achieves 8.64 % improvement in detecting fraudulent cases compared to the best baseline model. As such, our study advances the research frontier in fraud detection and contributes an innovative IT artifact in practice.

{"title":"Can earnings conference calls tell more lies? A contrastive multimodal dialogue network for advanced financial statement fraud detection","authors":"Qi Lu , Wei Du , Shaochen Yang , Wei Xu , J. Leon Zhao","doi":"10.1016/j.dss.2024.114381","DOIUrl":"10.1016/j.dss.2024.114381","url":null,"abstract":"<div><div>Financial statement frauds by listed firms pose significant challenges to public investors and jeopardize the stability of financial markets. Previous studies have identified deceptive verbal and vocal cues from earnings conference calls as indicators of financial statement fraud. However, these studies only extracted managers' verbal and vocal cues separately over the entire call, neglecting the utterance-level fusion between verbal and vocal cues as well as the multi-turn interaction between analysts and managers. To fill this gap, we develop a novel end-to-end <em><strong>c</strong>ontrastive <strong>m</strong>ulti<strong>m</strong>odal <strong>d</strong>ialogue network</em> (CMMD) that considers both verbal-vocal fusion and multi-role interactions to uncover hidden deceptive cues in earnings conference calls. The proposed model comprises two core modules, namely, the <em>Multimodal Fusion Learning module and the Dialogue Interaction Learning module</em>. Building on Vrij's verbal-nonverbal complementary mechanisms in deception detection, the designed <em>Multimodal Fusion Learning</em> employs contrastive learning to align verbal and vocal cues and a co-attention mechanism to learn cross-modal interaction. Inspired by the Interpersonal Deception Theory that emphasizes the dynamic interaction process between deceivers and targets, the <em>Dialogue Interaction Learning</em> utilizes a dialogue-aware co-attention mechanism to model multi-turn analyst-manager interaction and uses contrastive learning to improve dialogue representations. Our extensive empirical results show that CMMD achieves 8.64 % improvement in detecting fraudulent cases compared to the best baseline model. As such, our study advances the research frontier in fraud detection and contributes an innovative IT artifact in practice.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"189 ","pages":"Article 114381"},"PeriodicalIF":6.7,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143170849","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

Should a better-informed manufacturer hold pricing power for the direct channel: The role of consumer reviews

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

Decision Support Systems

Pub Date : 2025-01-31 DOI: 10.1016/j.dss.2025.114408

Musen Xue , Jiahui Guo , Lin Feng

Manufacturers can effectively obtain precise demand information through the utilization of data analysis technologies. These better-informed manufacturers commonly distribute their products not only through traditional offline retailers but also via direct sales channels. In this context, distinct pricing strategies for online channels, namely holding pricing power and giving up pricing power, can be observed in practice. Furthermore, these online channels also enable consumers to post consumer reviews, which significantly impacts consumers’ purchasing decisions. By applying a signaling game, our study examines the interaction between pricing strategy of a direct sales channel and consumer reviews. Our findings indicate that consumer reviews significantly influence the determination of the optimal pricing strategy of direct channel for a better-informed manufacturer. Holding pricing power is always the optimal strategy when the direct channel functions as an authentic distribution channel. However, giving up pricing power can be optimal when the direct channel personates a competitive threat, conditional on the travel cost of traditional channel and the information disclosed through consumer reviews. Contrary to expectations, manufacturer’s retention of pricing power for the direct channel can benefit the retailer when the travel cost to the traditional channel is moderate and the information disclosed in consumer reviews does not exhibit extreme negativity or positivity. Additionally, our findings indicate that the chain members can acquire an agreement on the direct channel’s pricing strategy, which results in a win-win outcome, thereby improving supply chain efficiency.

{"title":"Should a better-informed manufacturer hold pricing power for the direct channel: The role of consumer reviews","authors":"Musen Xue , Jiahui Guo , Lin Feng","doi":"10.1016/j.dss.2025.114408","DOIUrl":"10.1016/j.dss.2025.114408","url":null,"abstract":"<div><div>Manufacturers can effectively obtain precise demand information through the utilization of data analysis technologies. These better-informed manufacturers commonly distribute their products not only through traditional offline retailers but also via direct sales channels. In this context, distinct pricing strategies for online channels, namely holding pricing power and giving up pricing power, can be observed in practice. Furthermore, these online channels also enable consumers to post consumer reviews, which significantly impacts consumers’ purchasing decisions. By applying a signaling game, our study examines the interaction between pricing strategy of a direct sales channel and consumer reviews. Our findings indicate that consumer reviews significantly influence the determination of the optimal pricing strategy of direct channel for a better-informed manufacturer. Holding pricing power is always the optimal strategy when the direct channel functions as an authentic distribution channel. However, giving up pricing power can be optimal when the direct channel personates a competitive threat, conditional on the travel cost of traditional channel and the information disclosed through consumer reviews. Contrary to expectations, manufacturer’s retention of pricing power for the direct channel can benefit the retailer when the travel cost to the traditional channel is moderate and the information disclosed in consumer reviews does not exhibit extreme negativity or positivity. Additionally, our findings indicate that the chain members can acquire an agreement on the direct channel’s pricing strategy, which results in a win-win outcome, thereby improving supply chain efficiency.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114408"},"PeriodicalIF":6.7,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169045","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

Tell me a story! Narrative-driven XAI with Large Language Models

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

Decision Support Systems

Pub Date : 2025-01-31 DOI: 10.1016/j.dss.2025.114402

David Martens , James Hinns , Camille Dams , Mark Vergouwen , Theodoros Evgeniou

Existing Explainable AI (XAI) approaches, such as the widely used SHAP values or counterfactual (CF) explanations, are arguably often too technical for users to understand and act upon. To enhance comprehension of explanations of AI decisions and the overall user experience, we introduce XAIstories, which leverage Large Language Models (LLMs) to provide narratives about how AI predictions are made: SHAPstories based on SHAP and CFstories on CF explanations. We study the impact of our approach on users’ experience and understanding of AI predictions. Our results are striking: over 90% of the surveyed general audience finds the narratives generated by SHAPstories convincing, and over 78% for CFstories, in a tabular data experiment. More than 75% of the respondents in an image experiment find CFstories more or equally convincing as their own crafted stories. We also find that the generated stories help users to more accurately summarize and understand AI decisions than they do when only SHAP values are provided. The results indicate that combining LLM generated stories with current XAI methods is a promising and impactful research direction.

现有的可解释人工智能（XAI）方法，如广泛使用的SHAP值或反事实（CF）解释，可以说往往技术性太强，用户难以理解和操作。为了提高对人工智能决策解释的理解力和整体用户体验，我们引入了 XAIstories，它利用大型语言模型（LLM）来叙述人工智能预测是如何做出的：其中，SHAPstories 基于 SHAP，CFstories 基于 CF 解释。我们研究了我们的方法对用户体验和理解人工智能预测的影响。我们的研究结果令人震惊：在一项表格数据实验中，超过 90% 的受访普通用户认为 SHAPstories 所生成的叙述具有说服力，超过 78% 的受访普通用户认为 CFstories 所生成的叙述具有说服力。在图像实验中，超过 75% 的受访者认为 CFstories 与他们自己创作的故事更有说服力或同样有说服力。我们还发现，与只提供 SHAP 值时相比，生成的故事能帮助用户更准确地总结和理解人工智能决策。这些结果表明，将 LLM 生成的故事与当前的 XAI 方法相结合是一个很有前景和影响力的研究方向。

{"title":"Tell me a story! Narrative-driven XAI with Large Language Models","authors":"David Martens , James Hinns , Camille Dams , Mark Vergouwen , Theodoros Evgeniou","doi":"10.1016/j.dss.2025.114402","DOIUrl":"10.1016/j.dss.2025.114402","url":null,"abstract":"<div><div>Existing Explainable AI (XAI) approaches, such as the widely used SHAP values or counterfactual (CF) explanations, are arguably often too technical for users to understand and act upon. To enhance comprehension of explanations of AI decisions and the overall user experience, we introduce XAIstories, which leverage Large Language Models (LLMs) to provide narratives about how AI predictions are made: SHAPstories based on SHAP and CFstories on CF explanations. We study the impact of our approach on users’ experience and understanding of AI predictions. Our results are striking: over 90% of the surveyed general audience finds the narratives generated by SHAPstories convincing, and over 78% for CFstories, in a tabular data experiment. More than 75% of the respondents in an image experiment find CFstories more or equally convincing as their own crafted stories. We also find that the generated stories help users to more accurately summarize and understand AI decisions than they do when only SHAP values are provided. The results indicate that combining LLM generated stories with current XAI methods is a promising and impactful research direction.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114402"},"PeriodicalIF":6.7,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143193315","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

Multimodal review helpfulness prediction with a multi-level cognitive reasoning mechanism: A theory-driven graph learning model

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

Decision Support Systems

Pub Date : 2025-01-29 DOI: 10.1016/j.dss.2025.114406

Hai Wei , Ying Yang , Yu-Wang Chen

Customers' perception of review helpfulness entails a cognitive reasoning process influenced by the contextual information of reviews including product descriptions and review neighbors. Current studies on helpfulness prediction primarily focus on static features of individual reviews, neglecting the dynamic interaction among products, reviews and their contextual neighbors. To address this gap, we propose a theory-driven deep learning model for multimodal review helpfulness prediction (DeepMRHP-MCR). The model can collectively simulate human cognitive processes when voting on whether a review is helpful. Specifically, this study presents a multi-level cognitive reasoning mechanism that reconciles the inconsistencies among product descriptions, reviews and their neighbors from the modality, individual and contextual level, respectively. A case study is conducted on the real-world datasets collected from Amazon.com. Empirical results show that the proposed model can improve the quality and interpretability of review prediction process, and present a deep comprehension of consumer's cognitive decision-making process when evaluating reviews.

顾客对评论有用性的感知需要一个认知推理过程，这一过程受到包括产品描述和邻近评论在内的评论上下文信息的影响。目前有关有用性预测的研究主要关注单个评论的静态特征，而忽视了产品、评论及其上下文邻居之间的动态互动。为了弥补这一不足，我们提出了一种理论驱动的多模态评论有用性预测深度学习模型（DeepMRHP-MCR）。该模型可以共同模拟人类在投票决定评论是否有帮助时的认知过程。具体来说，本研究提出了一种多层次的认知推理机制，可分别从模态、个体和上下文三个层面来协调产品描述、评论及其邻居之间的不一致性。我们在亚马逊网站收集的真实世界数据集上进行了案例研究。实证结果表明，所提出的模型可以提高评论预测过程的质量和可解释性，并能深入理解消费者在评价评论时的认知决策过程。

{"title":"Multimodal review helpfulness prediction with a multi-level cognitive reasoning mechanism: A theory-driven graph learning model","authors":"Hai Wei , Ying Yang , Yu-Wang Chen","doi":"10.1016/j.dss.2025.114406","DOIUrl":"10.1016/j.dss.2025.114406","url":null,"abstract":"<div><div>Customers' perception of review helpfulness entails a cognitive reasoning process influenced by the contextual information of reviews including product descriptions and review neighbors. Current studies on helpfulness prediction primarily focus on static features of individual reviews, neglecting the dynamic interaction among products, reviews and their contextual neighbors. To address this gap, we propose a theory-driven deep learning model for multimodal review helpfulness prediction (DeepMRHP-MCR). The model can collectively simulate human cognitive processes when voting on whether a review is helpful. Specifically, this study presents a multi-level cognitive reasoning mechanism that reconciles the inconsistencies among product descriptions, reviews and their neighbors from the modality, individual and contextual level, respectively. A case study is conducted on the real-world datasets collected from <span><span>Amazon.com</span><svg><path></path></svg></span>. Empirical results show that the proposed model can improve the quality and interpretability of review prediction process, and present a deep comprehension of consumer's cognitive decision-making process when evaluating reviews.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"191 ","pages":"Article 114406"},"PeriodicalIF":6.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143193316","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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Decision Support Systems

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀