Pub Date : 2025-05-15DOI: 10.1016/j.elerap.2025.101510
Xingpeng Xu , Qingfeng Zeng , Ri Na , Weiguo Fan
It is known that streamers play a special role in live streaming commerce, but there is a huge discrepancy in sales performance resulting from different characteristics of streamers. This study applies social influence theory to systematically analyze how streamer characteristics interact to affect sales performance. Using a unique dataset of 120,794 live streaming records from 597 streamers on Douyin platform, we establish a fixed effects model with unbalanced panel data. The results show that previous sales have strong momentum effects. Total views, number of live commercial products and live streaming duration all have a positive impact on sales volumes. Heterogeneity analysis reveals significant differences across identity types, industry types, and authentication statuses, with celebrities, streamers from entertainment and leisure sectors, and unverified streamers showing notably stronger gains. These findings provide empirical evidence to guide streamers and platforms in optimizing marketing strategies in the competitive live streaming commerce.
{"title":"Unveiling the influence of streamer characteristics on sales performance in live streaming commerce","authors":"Xingpeng Xu , Qingfeng Zeng , Ri Na , Weiguo Fan","doi":"10.1016/j.elerap.2025.101510","DOIUrl":"10.1016/j.elerap.2025.101510","url":null,"abstract":"<div><div>It is known that streamers play a special role in live streaming commerce, but there is a huge discrepancy in sales performance resulting from different characteristics of streamers. This study applies social influence theory to systematically analyze how streamer characteristics interact to affect sales performance. Using a unique dataset of 120,794 live streaming records from 597 streamers on Douyin platform, we establish a fixed effects model with unbalanced panel data. The results show that previous sales have strong momentum effects. Total views, number of live commercial products and live streaming duration all have a positive impact on sales volumes. Heterogeneity analysis reveals significant differences across identity types, industry types, and authentication statuses, with celebrities, streamers from entertainment and leisure sectors, and unverified streamers showing notably stronger gains. These findings provide empirical evidence to guide streamers and platforms in optimizing marketing strategies in the competitive live streaming commerce.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"72 ","pages":"Article 101510"},"PeriodicalIF":5.9,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-05-01DOI: 10.1016/j.elerap.2025.101505
Xin Yan , Wenxin Wang , Yuanyuan Jiao
The information cocoon, a phenomenon prevalent on digital platforms, significantly influences customer experiences. However, its impact remains debated, and it is still unclear whether it facilitates or hinders customer engagement. This study develops and empirically tests a conditional process model to examine how the information cocoon influences customer stickiness within the context of e-commerce platforms. The findings indicate that the effect of the information cocoon on customer stickiness is dual-edged and contingent upon customers’ decision-making styles. In addition, the underlying mechanisms through which the information cocoon affects different dimensions of customer stickiness, namely purchase stickiness and visit stickiness, are not the same. This study expands the application scope and theoretical boundaries of the information cocoon concept, highlights its dual impact on customer stickiness, and deepens the theoretical understanding of how customer stickiness develops.
{"title":"Promoting or inhibiting? The impact of the information cocoon on customer stickiness in e-commerce platforms: The moderating role of decision-making style","authors":"Xin Yan , Wenxin Wang , Yuanyuan Jiao","doi":"10.1016/j.elerap.2025.101505","DOIUrl":"10.1016/j.elerap.2025.101505","url":null,"abstract":"<div><div>The information cocoon, a phenomenon prevalent on digital platforms, significantly influences customer experiences. However, its impact remains debated, and it is still unclear whether it facilitates or hinders customer engagement. This study develops and empirically tests a conditional process model to examine how the information cocoon influences customer stickiness within the context of e-commerce platforms. The findings indicate that the effect of the information cocoon on customer stickiness is dual-edged and contingent upon customers’ decision-making styles. In addition, the underlying mechanisms through which the information cocoon affects different dimensions of customer stickiness, namely purchase stickiness and visit stickiness, are not the same. This study expands the application scope and theoretical boundaries of the information cocoon concept, highlights its dual impact on customer stickiness, and deepens the theoretical understanding of how customer stickiness develops.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101505"},"PeriodicalIF":5.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-05-01DOI: 10.1016/j.elerap.2025.101506
Ankai Li , Li Wang , Haijun Yang , Harris Wu
The growth of content-sharing platforms facilitates the transfer of users to e-commerce sites. However, content-sharing platforms face copyright infringement issues related to content theft and platform invasion, dampening the flow of traffic to e-commerce. Traditional copyright protection methods lack effectiveness and efficiency, which can be solved by Non-Fungible Tokens (NFTs) stored on a blockchain. This study examines how a content-sharing platform adopts three NFT-based copyright protection strategies: the NFT-based copyright certification strategy to combat content theft, the NFT-based content moderation, and copyrighted material provision strategies to combat platform invasion. Our paper models a two-sided platform with content consumers and suppliers. Platform invasion occurs when suppliers bring copyright-infringing content to the platform, while content theft refers to content suppliers being pirated outside the platform. We identify the optimal combination of platform copyright protection strategies. The platform may adopt the copyright certification strategy to combat content theft. However, we show that the platform cannot benefit from adopting both content moderation and material provision strategies to counter platform invasion if the quantity of infringing materials used by infringers is small and the material provisioning costs of the platform are low. Moreover, there are mutually enhancing effects between content moderation and material provision strategies. Our study emphasizes the importance of NFT-based copyright protection strategies to content-sharing platforms and provides a comprehensive framework for understanding the implications of copyright certification, content moderation, and copyrighted material provision.
{"title":"Content-sharing platforms’ copyright protection strategies with non-fungible tokens","authors":"Ankai Li , Li Wang , Haijun Yang , Harris Wu","doi":"10.1016/j.elerap.2025.101506","DOIUrl":"10.1016/j.elerap.2025.101506","url":null,"abstract":"<div><div>The growth of content-sharing platforms facilitates the transfer of users to e-commerce sites. However, content-sharing platforms face copyright infringement issues related to content theft and platform invasion, dampening the flow of traffic to e-commerce. Traditional copyright protection methods lack effectiveness and efficiency, which can be solved by Non-Fungible Tokens (NFTs) stored on a blockchain. This study examines how a content-sharing platform adopts three NFT-based copyright protection strategies: the NFT-based copyright certification strategy to combat content theft, the NFT-based content moderation, and copyrighted material provision strategies to combat platform invasion. Our paper models a two-sided platform with content consumers and suppliers. Platform invasion occurs when suppliers bring copyright-infringing content to the platform, while content theft refers to content suppliers being pirated outside the platform. We identify the optimal combination of platform copyright protection strategies. The platform may adopt the copyright certification strategy to combat content theft. However, we show that the platform cannot benefit from adopting both content moderation and material provision strategies to counter platform invasion if the quantity of infringing materials used by infringers is small and the material provisioning costs of the platform are low. Moreover, there are mutually enhancing effects between content moderation and material provision strategies. Our study emphasizes the importance of NFT-based copyright protection strategies to content-sharing platforms and provides a comprehensive framework for understanding the implications of copyright certification, content moderation, and copyrighted material provision.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101506"},"PeriodicalIF":5.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144069200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-05-01DOI: 10.1016/j.elerap.2025.101503
Lu Wang , Min Zhang , Yiwei Li
In order to improve the information exchange between customers, the social development of online review systems enables customers to interact with focal customers by responding to initial reviews. Our purpose is to investigate the effect of customer responses (CRs) on subsequent customer rating behavior. Based on cue utilization theory, we hypothesize that CRs minimize fit uncertainty, resulting in better customer and product fits, and eventually high ratings. We examine whether and how CRs affect subsequent ratings through cross-platform difference-in-differences and within-platform identification strategies. The results show that CRs have significant positive effects on subsequent ratings. The features of CR, including CR content, CR sentiment, and CR timeliness have an impact on the subsequent review rating. Additionally, rating variance positively moderates CRs’ effect. This study contributes to the customer-to-customer interactions literature and provides practical guidance for customers, platforms, and businesses to manage and leverage online reviews.
{"title":"The power of C2C interactions: Effect of customer responses to online reviews on subsequent ratings","authors":"Lu Wang , Min Zhang , Yiwei Li","doi":"10.1016/j.elerap.2025.101503","DOIUrl":"10.1016/j.elerap.2025.101503","url":null,"abstract":"<div><div>In order to improve the information exchange between customers, the social development of online review systems enables customers to interact with focal customers by responding to initial reviews. Our purpose is to investigate the effect of customer responses (CRs) on subsequent customer rating behavior. Based on cue utilization theory, we hypothesize that CRs minimize fit uncertainty, resulting in better customer and product fits, and eventually high ratings. We examine whether and how CRs affect subsequent ratings through cross-platform difference-in-differences and within-platform identification strategies. The results show that CRs have significant positive effects on subsequent ratings. The features of CR, including CR content, CR sentiment, and CR timeliness have an impact on the subsequent review rating. Additionally, rating variance positively moderates CRs’ effect. This study contributes to the customer-to-customer interactions literature and provides practical guidance for customers, platforms, and businesses to manage and leverage online reviews.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101503"},"PeriodicalIF":5.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-05-01DOI: 10.1016/j.elerap.2025.101500
Yushuo Cao , Wei Zhong Wang , Yajing Zhang , Muhammet Deveci , Seifedine Kadry , Limin Wang
The exchange of goods on e-commerce platforms has become an essential channel in contemporary digital landscapes. Utilizing data-driven nudging as a strategic approach to shaping consumer behavior should consider numerous influential factors. Nevertheless, there remains a deficiency in analyzing the factors that facilitate the implementation of data-driven nudging on e-commerce platforms. This work explores the influencing factors of data-driven nudging adoption in e-commerce platforms using a probabilistic linguistic decision framework that incorporates the DEMATEL (decision-making trail and evaluation laboratory)-ISM (interpretive structural modeling) method. To uncover the challenges and opportunities of using data-driven nudging for e-commerce platforms, we identify sixteen influencing factors based on SWOT (strengths, weaknesses, opportunities, and threats) and a literature review. Then, the probabilistic linguistic DEMATEL method is introduced to depict the interaction relationships among these factors. Subsequently, the ISM method is used to build these factors’ contextual linkages and hierarchical structures. Finally, we conducted a questionnaire survey to obtain the data for the analysis framework. The results show that the main strength is “the desirability of handling and utilizing a product ()”, the main weakness is “misdirection ()”, the primary opportunity is “Making appropriate policies ()”, and the main threat is “affecting freedom and autonomy ()”. Our research provides a new analytical tool for identifying the factors that utilize data-driven nudging in e-commerce platforms, offering practical implications for both e-commerce platforms and merchants.
{"title":"Analyzing adoption factors of data-driven nudging for e-commerce platforms using an integrated decision model","authors":"Yushuo Cao , Wei Zhong Wang , Yajing Zhang , Muhammet Deveci , Seifedine Kadry , Limin Wang","doi":"10.1016/j.elerap.2025.101500","DOIUrl":"10.1016/j.elerap.2025.101500","url":null,"abstract":"<div><div>The exchange of goods on e-commerce platforms has become an essential channel in contemporary digital landscapes. Utilizing data-driven nudging as a strategic approach to shaping consumer behavior should consider numerous influential factors. Nevertheless, there remains a deficiency in analyzing the factors that facilitate the implementation of data-driven nudging on e-commerce platforms. This work explores the influencing factors of data-driven nudging adoption in e-commerce platforms using a probabilistic linguistic decision framework that incorporates the DEMATEL (decision-making trail and evaluation laboratory)-ISM (interpretive structural modeling) method. To uncover the challenges and opportunities of using data-driven nudging for e-commerce platforms, we identify sixteen influencing factors based on SWOT (strengths, weaknesses, opportunities, and threats) and a literature review. Then, the probabilistic linguistic DEMATEL method is introduced to depict the interaction relationships among these factors. Subsequently, the ISM method is used to build these factors’ contextual linkages and hierarchical structures. Finally, we conducted a questionnaire survey to obtain the data for the analysis framework. The results show that the main strength is “the desirability of handling and utilizing a product (<span><math><msub><mi>θ</mi><mn>4</mn></msub></math></span>)”, the main weakness is “misdirection (<span><math><msub><mi>θ</mi><mn>5</mn></msub></math></span>)”, the primary opportunity is “Making appropriate policies (<span><math><msub><mi>θ</mi><mn>12</mn></msub></math></span>)”, and the main threat is “affecting freedom and autonomy (<span><math><msub><mi>θ</mi><mn>13</mn></msub></math></span>)”. Our research provides a new analytical tool for identifying the factors that utilize data-driven nudging in e-commerce platforms, offering practical implications for both e-commerce platforms and merchants.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101500"},"PeriodicalIF":5.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-11DOI: 10.1016/j.elerap.2025.101502
Huiran Li , Qiucheng Li , Baozhu Feng
In search engine advertising (SEA) market, where competition among retailers is intense and multifaceted, channel coordination between retailers and manufacturers emerges as a critical factor, which significantly influences the effectiveness of advertising strategies. This research attempts to provide managerial guidelines for cooperative advertising in the SEA context by modeling two cooperative advertising decision scenarios. Scenario I defines a simple cooperative channel consisting of one manufacturer and one retailer. In Scenario II, we consider a more general setting where there is an independent retailer who competes with the Manufacturer-Retailer alliance in Scenario I. We propose a novel cooperative advertising optimization model, wherein a manufacturer can advertise product directly through SEA campaigns and indirectly by subsidizing its retailer. To highlight the distinctive features of SEA, our model incorporates dynamic quality scores and focuses on a finite time horizon. In each scenario, we provide a feasible equilibrium solution of optimal policies for all members. Subsequently, we conduct numerical experiments to perform sensitivity analysis for both the quality score and gross margin. Additionally, we explore the impact of the initial market share of the competing retailer in Scenario II. Finally, we investigate how retail competition affects the cooperative alliance’s optimal strategy and channel performance. Our identified properties derived from the equilibrium and numerical analyses offer crucial insights for participants engaged in cooperative advertising within the SEA market.
{"title":"Dynamic cooperative strategies in search engine advertising market: With and without retail competition","authors":"Huiran Li , Qiucheng Li , Baozhu Feng","doi":"10.1016/j.elerap.2025.101502","DOIUrl":"10.1016/j.elerap.2025.101502","url":null,"abstract":"<div><div>In search engine advertising (SEA) market, where competition among retailers is intense and multifaceted, channel coordination between retailers and manufacturers emerges as a critical factor, which significantly influences the effectiveness of advertising strategies. This research attempts to provide managerial guidelines for cooperative advertising in the SEA context by modeling two cooperative advertising decision scenarios. Scenario I defines a simple cooperative channel consisting of one manufacturer and one retailer. In Scenario II, we consider a more general setting where there is an independent retailer who competes with the Manufacturer-Retailer alliance in Scenario I. We propose a novel cooperative advertising optimization model, wherein a manufacturer can advertise product directly through SEA campaigns and indirectly by subsidizing its retailer. To highlight the distinctive features of SEA, our model incorporates dynamic quality scores and focuses on a finite time horizon. In each scenario, we provide a feasible equilibrium solution of optimal policies for all members. Subsequently, we conduct numerical experiments to perform sensitivity analysis for both the quality score and gross margin. Additionally, we explore the impact of the initial market share of the competing retailer in Scenario II. Finally, we investigate how retail competition affects the cooperative alliance’s optimal strategy and channel performance. Our identified properties derived from the equilibrium and numerical analyses offer crucial insights for participants engaged in cooperative advertising within the SEA market.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101502"},"PeriodicalIF":5.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-05DOI: 10.1016/j.elerap.2025.101499
Wang Zhao , Dongxiao Gu , Rui Mao , Xiaoyu Wang , Xuejie Yang , Kaixuan Zhu , Hao Hu , Haimiao Mo , Erik Cambria
The COVID-19 pandemic has markedly exacerbated the complexities surrounding the diagnosis and prognosis of diverse severe pneumonia types, posing extraordinary challenges to healthcare systems worldwide. While previous AI-based approaches primarily targeted COVID-19 severe pneumonia and sought to enhance machine learning accuracy, they often neglected critical aspects such as distinguishing diagnostic and prognostic features among COVID-19 infectious, non-COVID infectious, and non-infectious severe pneumonia, as well as the explainability and fairness of user-centric AI assist decisions. This study es the need for robust, fair, and reliable diagnosis and prognosis of severe pneumonia within the context of the COVID-19 pandemic. This paper introduces a user-centric framework that first employs a GaussianCopula-based data augmentation method to enhance fairness by addressing small imbalanced sample sets. Following this, the framework introduces an explainable AI system designed to classify three types of severe pneumonia using demographic and physiological indicators, offering transparent decision-making processes and an understandable analysis of prognosis risk factors. Our fair system utilizes transparent models exclusively, which enables healthcare practitioners to access intelligent and reliable medical services such as pre-diagnosis and prognosis analysis (the likelihood of death) of severe pneumonia. The results show the data augmentation method efficiently reduces data bias and enhances fairness, reaching 70.70% distribution similarity. Our transparent model-based severe pneumonia classification module achieves 98.88% F1-scores on a real-world dataset. The transparent mechanism reveals that the four most significant features for classifying severe pneumonia types are ‘Interleukin_6’, ‘Albumin’, ‘D_Dimer’, and ‘CD4_absolute_count’. Meanwhile, the explainable statistical analysis identifies critical mortality risk factors for each pneumonia category: ‘Blood platelet’ and ‘Creatinine’ for COVID-19 severe pneumonia, ‘Hemameba’, ‘Interleukin-6’, and ‘Uric Acid’ for non-COVID-19 infectious severe pneumonia, and ‘Hemameba’, ‘BNP’, ‘Cholesterol’, and ‘PT’ for non-infectious severe pneumonia. Our study highlights the potential of transparent machine learning algorithms for accurate diagnosis and Cox proportional regression for transparent risk trend prediction. These analytical tools and medical results can facilitate early and appropriate management of pneumonia patients for doctors, potentially revolutionizing diagnostic processes and patient care strategies to improve clinical outcomes.
{"title":"Explainable, robust and fair user-centric AI system for the diagnosis and prognosis of severe pneumonia","authors":"Wang Zhao , Dongxiao Gu , Rui Mao , Xiaoyu Wang , Xuejie Yang , Kaixuan Zhu , Hao Hu , Haimiao Mo , Erik Cambria","doi":"10.1016/j.elerap.2025.101499","DOIUrl":"10.1016/j.elerap.2025.101499","url":null,"abstract":"<div><div>The COVID-19 pandemic has markedly exacerbated the complexities surrounding the diagnosis and prognosis of diverse severe pneumonia types, posing extraordinary challenges to healthcare systems worldwide. While previous AI-based approaches primarily targeted COVID-19 severe pneumonia and sought to enhance machine learning accuracy, they often neglected critical aspects such as distinguishing diagnostic and prognostic features among COVID-19 infectious, non-COVID infectious, and non-infectious severe pneumonia, as well as the explainability and fairness of user-centric AI assist decisions. This study es the need for robust, fair, and reliable diagnosis and prognosis of severe pneumonia within the context of the COVID-19 pandemic. This paper introduces a user-centric framework that first employs a GaussianCopula-based data augmentation method to enhance fairness by addressing small imbalanced sample sets. Following this, the framework introduces an explainable AI system designed to classify three types of severe pneumonia using demographic and physiological indicators, offering transparent decision-making processes and an understandable analysis of prognosis risk factors. Our fair system utilizes transparent models exclusively, which enables healthcare practitioners to access intelligent and reliable medical services such as pre-diagnosis and prognosis analysis (the likelihood of death) of severe pneumonia. The results show the data augmentation method efficiently reduces data bias and enhances fairness, reaching 70.70% distribution similarity. Our transparent model-based severe pneumonia classification module achieves 98.88% F1-scores on a real-world dataset. The transparent mechanism reveals that the four most significant features for classifying severe pneumonia types are ‘Interleukin_6’, ‘Albumin’, ‘D_Dimer’, and ‘CD4_absolute_count’. Meanwhile, the explainable statistical analysis identifies critical mortality risk factors for each pneumonia category: ‘Blood platelet’ and ‘Creatinine’ for COVID-19 severe pneumonia, ‘Hemameba’, ‘Interleukin-6’, and ‘Uric Acid’ for non-COVID-19 infectious severe pneumonia, and ‘Hemameba’, ‘BNP’, ‘Cholesterol’, and ‘PT’ for non-infectious severe pneumonia. Our study highlights the potential of transparent machine learning algorithms for accurate diagnosis and Cox proportional regression for transparent risk trend prediction. These analytical tools and medical results can facilitate early and appropriate management of pneumonia patients for doctors, potentially revolutionizing diagnostic processes and patient care strategies to improve clinical outcomes.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101499"},"PeriodicalIF":5.9,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-01DOI: 10.1016/j.elerap.2025.101498
Shoujie Cai , Sijie Li , Yiding Liu , Xiaohua Han
Livestreaming e-commerce has emerged as a highly effective online shopping format, capturing significant attention from manufacturers and retailers. A novel variant, self-livestreaming, is gaining traction. When manufacturers conduct multiple self-livestreaming events across different platforms, each livestreaming room or streamer resonates differently with consumers. In this context, two distinct consumer segments emerge: loyal consumers and regular consumers. This study examines the dual self-livestreaming strategy adopted by manufacturers, incorporating factors including room attractiveness and consumer types to determine the optimal pricing and sequencing for three distinct livestreaming strategies: S (simultaneous livestreaming in both rooms), L (the low-attractiveness room livestreams first), and H (the high-attractiveness room livestreams first). The results reveal that a lower proportion of loyal consumers or higher room attractiveness leads to greater profits for manufacturers. Moreover, the choice of livestreaming strategy for manufacturers varies based on room attractiveness and the proportions of the two consumer types. In the extended model, we analyze the impact of operational costs on the decision to use one or two rooms, particularly when the low-attractiveness room has no loyal consumers. Specifically, we explore how room attractiveness and the proportion of regular consumers influence room adoption decisions. These insights not only provide practical operational guidance but also enrich the existing literature on self-livestreaming operations.
{"title":"Who should livestream first? Sequence of dual self-livestreaming rooms for manufacturers","authors":"Shoujie Cai , Sijie Li , Yiding Liu , Xiaohua Han","doi":"10.1016/j.elerap.2025.101498","DOIUrl":"10.1016/j.elerap.2025.101498","url":null,"abstract":"<div><div>Livestreaming e-commerce has emerged as a highly effective online shopping format, capturing significant attention from manufacturers and retailers. A novel variant, self-livestreaming, is gaining traction. When manufacturers conduct multiple self-livestreaming events across different platforms, each livestreaming room or streamer resonates differently with consumers. In this context, two distinct consumer segments emerge: loyal consumers and regular consumers. This study examines the dual self-livestreaming strategy adopted by manufacturers, incorporating factors including room attractiveness and consumer types to determine the optimal pricing and sequencing for three distinct livestreaming strategies: S (simultaneous livestreaming in both rooms), L (the low-attractiveness room livestreams first), and H (the high-attractiveness room livestreams first). The results reveal that a lower proportion of loyal consumers or higher room attractiveness leads to greater profits for manufacturers. Moreover, the choice of livestreaming strategy for manufacturers varies based on room attractiveness and the proportions of the two consumer types. In the extended model, we analyze the impact of operational costs on the decision to use one or two rooms, particularly when the low-attractiveness room has no loyal consumers. Specifically, we explore how room attractiveness and the proportion of regular consumers influence room adoption decisions. These insights not only provide practical operational guidance but also enrich the existing literature on self-livestreaming operations.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101498"},"PeriodicalIF":5.9,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-30DOI: 10.1016/j.elerap.2025.101501
Yuejun Wang , Ding Wu , Xiangbin Yan
Social media platforms have begun to widely adopt the Pay-What-You-Want (PWYW) pricing model to sell User-Generated-Content (UGC). However, it is still under-explored why social media users voluntarily pay for UGC even if they can easily free-ride under PWYW conditions. In this paper, we theoretically derive and examine a model to understand users’ PWYW behaviors for UGC on social media. Drawing on social exchange theory, we treat perceived worth as the core antecedent and analyze the benefits and costs associated with users’ PWYW behaviors. In addition, we also propose that users’ PWYW experience and social endorsement are important contextual factors and examine their roles in shaping users’ PWYW decisions. To test the research model, we conducted an online survey study, and the results revealed two major findings. First, social media users mainly value the reciprocity for product and pleasure brought by PWYW behaviors but are also concerned about the perceived opportunity cost and inconvenience of e-payment process, based on which they form perceived worth that further determines their PWYW frequency. Second, social media users’ PWYW experience and social endorsement also influence their PWYW frequency, and the effects are partially and fully mediated by perceived worth, respectively. Our research reveals the crucial factors that motivate social media users’ PWYW engagement in UGC consumption and lays the foundation for future theoretical research and practical work.
社交媒体平台已开始广泛采用 "按需付费"（PWYW）的定价模式来销售用户生成内容（UGC）。然而，对于社交媒体用户为什么会自愿为 UGC 付费（即使在 PWYW 条件下他们可以轻松免费搭车），我们的研究还不够深入。在本文中，我们从理论上推导并研究了一个模型，以理解用户在社交媒体上为 UGC 付费的行为。借鉴社会交换理论，我们将感知价值作为核心前因，并分析了与用户 "PWYW "行为相关的收益和成本。此外，我们还提出用户的惠益行为体验和社会认可是重要的情境因素，并研究了它们在影响用户惠益行为决策中的作用。为了检验研究模型，我们进行了一项在线调查研究，结果显示了两大发现。首先，社交媒体用户主要看重 "想买就买 "行为带来的产品互惠和愉悦，但同时也关注电子支付过程中的感知机会成本和不便，在此基础上形成的感知价值进一步决定了他们的 "想买就买 "频率。其次，社交媒体用户的惠益行为体验和社会认可也会影响他们的惠益行为频率，而这两种效应分别部分和完全受到感知价值的中介作用。我们的研究揭示了促使社交媒体用户参与 UGC 消费的关键因素，为今后的理论研究和实践工作奠定了基础。
{"title":"You are worth my tipping: Why do people voluntarily pay for User-Generated-Content on social media platforms?","authors":"Yuejun Wang , Ding Wu , Xiangbin Yan","doi":"10.1016/j.elerap.2025.101501","DOIUrl":"10.1016/j.elerap.2025.101501","url":null,"abstract":"<div><div>Social media platforms have begun to widely adopt the Pay-What-You-Want (PWYW) pricing model to sell User-Generated-Content (UGC). However, it is still under-explored why social media users voluntarily pay for UGC even if they can easily free-ride under PWYW conditions. In this paper, we theoretically derive and examine a model to understand users’ PWYW behaviors for UGC on social media. Drawing on social exchange theory, we treat perceived worth as the core antecedent and analyze the benefits and costs associated with users’ PWYW behaviors. In addition, we also propose that users’ PWYW experience and social endorsement are important contextual factors and examine their roles in shaping users’ PWYW decisions. To test the research model, we conducted an online survey study, and the results revealed two major findings. <em>First</em>, social media users mainly value the reciprocity for product and pleasure brought by PWYW behaviors but are also concerned about the perceived opportunity cost and inconvenience of e-payment process, based on which they form perceived worth that further determines their PWYW frequency. <em>Second,</em> social media users’ PWYW experience and social endorsement also influence their PWYW frequency, and the effects are partially and fully mediated by perceived worth, respectively. Our research reveals the crucial factors that motivate social media users’ PWYW engagement in UGC consumption and lays the foundation for future theoretical research and practical work.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101501"},"PeriodicalIF":5.9,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-24DOI: 10.1016/j.elerap.2025.101493
Rongzheng Xiang , Jiajin Huang , Jian Yang
Sequential recommendation is of paramount importance for predicting user preferences based on their historical interactions. Recent studies have leveraged contrastive learning as an auxiliary task to enhance sequence representations, with the goal of improving recommendation accuracy. However, an important challenge arises: random item masking, a key component of contrastive learning, while promoting robust representations through intricate semantic inference, may inadvertently distort the original sequence semantics to some extent. In contrast, methods that prioritize the preservation of sequence semantics tend to neglect the essential masking mechanism for robust representation learning. To address this issue, we propose a model called Contrastive Learning with Adversarial Masking (CLAM) for sequential recommendation. CLAM consists of three core components: an inference module, an occlusion module, and a multi-task learning paradigm. During training, the occlusion module is optimized to perturb the inference module in both recommendation generation and contrastive learning tasks by adaptively generating item embedding masks. This adversarial training framework enables CLAM to balance sequential pattern preservation with the acquisition of robust representations in the inference module for recommendation tasks. Our extensive experiments on four benchmark datasets demonstrate the effectiveness of CLAM. It achieves significant improvements in sequential recommendation accuracy and robustness against noisy interactions.
{"title":"Contrastive learning with adversarial masking for sequential recommendation","authors":"Rongzheng Xiang , Jiajin Huang , Jian Yang","doi":"10.1016/j.elerap.2025.101493","DOIUrl":"10.1016/j.elerap.2025.101493","url":null,"abstract":"<div><div>Sequential recommendation is of paramount importance for predicting user preferences based on their historical interactions. Recent studies have leveraged contrastive learning as an auxiliary task to enhance sequence representations, with the goal of improving recommendation accuracy. However, an important challenge arises: random item masking, a key component of contrastive learning, while promoting robust representations through intricate semantic inference, may inadvertently distort the original sequence semantics to some extent. In contrast, methods that prioritize the preservation of sequence semantics tend to neglect the essential masking mechanism for robust representation learning. To address this issue, we propose a model called <strong>C</strong>ontrastive <strong>L</strong>earning with <strong>A</strong>dversarial <strong>M</strong>asking (CLAM) for sequential recommendation. CLAM consists of three core components: an inference module, an occlusion module, and a multi-task learning paradigm. During training, the occlusion module is optimized to perturb the inference module in both recommendation generation and contrastive learning tasks by adaptively generating item embedding masks. This adversarial training framework enables CLAM to balance sequential pattern preservation with the acquisition of robust representations in the inference module for recommendation tasks. Our extensive experiments on four benchmark datasets demonstrate the effectiveness of CLAM. It achieves significant improvements in sequential recommendation accuracy and robustness against noisy interactions.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"71 ","pages":"Article 101493"},"PeriodicalIF":5.9,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号