Electronic Commerce Research and Applications最新文献

{"title":"AI or manual customer service? Post-sale customer service strategy of EPSC considering consumers’ return behavior under different CRI modes","authors":"Yufei Wang ,&nbsp;Fengmin Yao ,&nbsp;FaXin Cheng ,&nbsp;Yingluo Yan","doi":"10.1016/j.elerap.2026.101587","DOIUrl":"10.1016/j.elerap.2026.101587","url":null,"abstract":"<div><div>Traditional customer service, once based on direct human interaction, is increasingly replaced by artificial intelligence (AI) interfaces, which are reshaping consumers’ post-sale experiences and merchants’ post-sale assurance mechanisms. This study examines how different service modes (manual vs. AI) interact with complimentary return-freight insurance (CRI) to determine post-sale outcomes within an e-commerce platform supply chain (EPSC). A Stackelberg game model is developed to analyze the strategic interactions between the platform and the merchant under four configurations (manual or AI customer service, with or without CRI), incorporating the emotional-void effect of AI customer service and the influence of manual compensation. The analytical results reveal that return convenience outweighs price sensitivity in stimulating demand, whereas excessive manual compensation reduces profits for all parties. Moreover, the merchant prefers manual customer service when CRI is available, but may switch to AI service once compensation becomes sufficiently high. Counterintuitively, the merchant is more likely to adopt CRI under the AI customer service mode. Unlike previous studies that exclusively focus on pre-sale AI applications, this research formalizes the post-sale emotional-void and compensation mechanisms, thereby extending technology-adoption theory and offering guidance for assurance policies in platform-governed supply chains.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101587"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147398946","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}

{"title":"Coping with e-commerce filter bubbles: proactive versus reactive strategies","authors":"Lei Hou ,&nbsp;Yichen Huang ,&nbsp;Xue Pan","doi":"10.1016/j.elerap.2026.101584","DOIUrl":"10.1016/j.elerap.2026.101584","url":null,"abstract":"<div><div>Personalized recommendations on e-commerce platforms enhance user experience and drive sales but may also create filter bubbles, limiting consumer exposure to diverse products and potentially leading to poor purchase decisions. While previous studies have primarily focused on algorithmic solutions, they have overlooked the active role of consumers in coping with filter bubbles. Building upon Protection Motivation Theory, this study explores how consumers’ threat appraisal and coping appraisal jointly drive their motivation to adopt proactive and reactive coping strategies. Analysis of survey data (<span><math><mrow><mi>N</mi><mo>=</mo><mn>386</mn></mrow></math></span>) reveals that higher perceived vulnerability and severity of filter bubbles increase both proactive and reactive coping motivations. The perceived benefits of personalized recommendations directly deter only reactive coping, while its impact on proactive coping is mediated by threat appraisal and coping cost. For coping appraisal, consumers are more motivated to adopt either proactive or reactive coping when they perceive higher efficacy or lower cost of the strategy. This study provides a novel perspective by integrating user-centric coping mechanisms into the discussion of filter bubbles, particularly highlighting the dual nature of personalized recommendations and how their benefits and threats interactively shape consumer behaviors.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101584"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173973","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}

{"title":"Stance detection for customer advocacy identification in online customer engagement: A deep learning approach","authors":"Bilal Abu-Salih ,&nbsp;Ruba Abu Khurma ,&nbsp;Ahmad K. Al Hwaitat ,&nbsp;Malak Al-Hassan ,&nbsp;Abeer F. Alkhwaldi ,&nbsp;Muder Almiani","doi":"10.1016/j.elerap.2026.101583","DOIUrl":"10.1016/j.elerap.2026.101583","url":null,"abstract":"<div><div>Customer advocacy is increasingly recognised as one of the most valuable outcomes of brand–consumer relationships. Unlike simple measures of satisfaction or sentiment, advocacy captures whether customers are willing to publicly endorse, recommend, or defend a brand. Yet measuring advocacy in online environments remains difficult: much of the existing work in sentiment analysis cannot distinguish between general positivity and brand-related support. In this paper, we propose a stance detection approach that is designed specifically to capture advocacy in brand–customer exchanges on social media. To model these interactions, we introduce a hybrid architecture that combines ELECTRA embeddings, a hierarchical attention bidirectional GRU to capture brand reply discourse, and capsule networks to preserve fine-grained stance cues. Our empirical evaluation shows that the proposed model achieves an overall Accuracy of 81.2%, Macro-F1 of 74.8%, and Cohen’s κ of 0.71, outperforming strong baselines such as BERT-base (Accuracy 74.6%, Macro-F1 67.5%) and ELECTRA-base (Accuracy 77.3%, Macro − F1 70.1%). The most notable gains are observed in the Antagonist class, where our model improves F1 from 58.1% (BERT) to 66.1%, effectively reducing misclassification of critical replies. Furthermore, stance proportions are strongly correlated with external measures of advocacy (Pearson’s r = 0.68 for Advocate share, r = -0.61 for Antagonist share), validating stance detection as a scalable proxy for monitoring advocacy. Our findings highlight how computational models of stance can advance both academic understanding and practical management of brand advocacy in Online Customer Engagement.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101583"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173994","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}

{"title":"Enhancing consumer engagement in virtual shopping: The role of social presence in shaping switching intentions","authors":"Xue Li ,&nbsp;Lanhui Cai ,&nbsp;Kum Fai Yuen","doi":"10.1016/j.elerap.2026.101580","DOIUrl":"10.1016/j.elerap.2026.101580","url":null,"abstract":"<div><div>Virtual shopping has emerged as a promising avenue for enhancing consumers’ retail experience, yet the understanding of presence in consumer switching behavior toward this emerging shopping channel remains limited. Drawing on a conceptual framework grounded in social presence theory, this study identifies the multidimensional structure of social presence and examines how its components shape consumers’ switching intentions, while also accounting for heterogeneity in demographic characteristics and shopping preferences. The study employs a self-administered questionnaire to collect data from 621 residents in Singapore. A second-order structural model is used to examine the the relationships among social presence, hedonic value, utilitarian value, perceived control, and switching intention. Moreover, a multi-group analysis is conducted to explore nuanced variations across certain demographic segments and product categories. Findings underscore the importance of social presence, hedonic value, and utilitarian value in shaping consumers’ switching behavior in virtual shopping environments. Moreover, the findings indicate that gender, product type, and product function can significantly moderate the relationship between social presence and switching intention. This study enriches the concept of social presence and consumer behavioral intention in virtual shopping. Managerially, the research offers insights for enhancing virtual shopping experiences via prioritizing social interactions.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101580"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173993","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}

{"title":"When emotions become (in-) appropriate: How social-contextual factors moderate the effect of emotional expressions on investment decisions in reward-based crowdfunding","authors":"Maximilian Raab,&nbsp;Sebastian Schlauderer ,&nbsp;Sven Overhage","doi":"10.1016/j.elerap.2026.101579","DOIUrl":"10.1016/j.elerap.2026.101579","url":null,"abstract":"<div><div>Investment decisions in reward-based crowdfunding are significantly shaped by the emotional appeal of campaign presentations. However, it remains still largely unclear how intensively emotional expressions should be used to most effectively persuade investors to fund a project. Building upon Emotions as Social Information theory, which suggests that effective emotional expressions must match social expectations and be perceived as appropriate by recipients, we studied the effect of emotional expressions in the text, pictures, and pitch videos of 16,967 Kickstarter campaigns. We found that the impact of emotional expressions on the investment decision is curvilinear across all modalities, meaning that it deteriorates or even reverses with higher intensities. We also found that this effect is moderated by the nature of the relationship between the entrepreneur and investors and by the perceived economic risk under which the investment decision is made. These factors seem to influence investors’ tolerance of more intensive emotional expressions.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101579"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173974","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}

{"title":"What to recommend is when to recommend: Modeling multi-granularity repurchase cycles","authors":"Yin Tang ,&nbsp;Zezheng Li ,&nbsp;Xiaotong Ye ,&nbsp;Xiaotong Luo ,&nbsp;Yonghui Chen ,&nbsp;Xing Qiu","doi":"10.1016/j.elerap.2026.101574","DOIUrl":"10.1016/j.elerap.2026.101574","url":null,"abstract":"<div><div>State-of-the-art sequential recommenders excel at predicting <em>what</em> a user will buy next, yet often fail to predict <em>when</em>. This is due to a flawed assumption: that repurchase intervals follow a single, simple pattern. We empirically demonstrate that the distribution of repeated-purchase intervals (DRPI) is, in fact, a complex mixture: typically a dominant power-law trend overlaid with multiple periodic spikes at weekly, monthly, and other granularities. We formalize this as the <strong>Principle of Multi-Granularity Repurchase Cycles</strong>. Ignoring this multi-modal reality introduces systematic timing bias, especially for frequently repurchased items. In view of this principle, we propose <em>MgRIA</em>, a novel recommendation paradigm that explicitly models these cycles. <em>MgRIA</em> uses a multi-granularity timestamp embedding to disentangle coexisting periodicities and a distribution-aware scoring mechanism to predict repurchase likelihood over time. Across three real-world datasets (Equity, Tafeng, and Taobao), <em>MgRIA</em> outperforms strong neural baselines such as BERT4Rec, TiSASRec, RepeatNet and DPGN by up to 0.9 absolute points in Recall@K and 0.14 points in Time-MRR@10, with average gains of 0.66 Recall@K and 0.14 Time-MRR@10 on the public Tafeng and Taobao benchmarks. The model also provides interpretability by revealing the specific repurchase cycles driving its predictions. By operationalizing our discovered principle, <em>MgRIA</em> bridges the gap between predicting <em>what</em> and <em>when</em>, while we also discuss practical limitations regarding dataset recency, domain transferability and computational overhead in real-time deployments.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101574"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080550","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}

{"title":"The effect of exploratory behaviour on online shopping stickiness: the role of enjoyment and satiation","authors":"Carmen Antón ,&nbsp;Carmen Camarero ,&nbsp;Itziar Oltra ,&nbsp;Elias Vega","doi":"10.1016/j.elerap.2026.101585","DOIUrl":"10.1016/j.elerap.2026.101585","url":null,"abstract":"<div><div>Users frequently spend longer than anticipated browsing online stores, resulting in online shopping stickiness, i.e., the intention to prolong navigation time within a browsing session, irrespective of the number of websites visited. This research investigates how exploration behaviours and browsing objectives impact stickiness during online shopping sessions. Specifically, the work analyses what influence exploration modes (specific vs. diversive) and goals (purchase-oriented vs. search-oriented) have on user stickiness, with perceived enjoyment and satiation acting as mediating factors. Using two experiments in the context of online clothing shopping and a field study, this work emphasizes the role of situational browsing elements in shaping stickiness behaviour. The findings enrich e-commerce literature by shifting the perspective from external factors (e.g., product or site attributes) to in-store exploration behaviours. This research offers valuable insights for e-commerce platforms that aim to optimize website interfaces to improve consumer experience and boost consumer retention, such as aligning navigation and content with user intentions and utilizing cross-category suggestions.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"76 ","pages":"Article 101585"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173995","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}

{"title":"A scalable framework for ranking integration in large-scale online reviews: Integrating clustering and multi-attribute decision-making","authors":"Mengchun Ma ,&nbsp;Bin Yu ,&nbsp;Zeshui Xu","doi":"10.1016/j.elerap.2025.101570","DOIUrl":"10.1016/j.elerap.2025.101570","url":null,"abstract":"<div><div>The proliferation of online reviews has transformed consumer decision-making in the hospitality industry, yet information overload remains a critical challenge. This study proposes a novel hotel ranking framework that integrates cluster analysis with Multi-Attribute Decision-Making (MADM) methods to address the issue of preference differences in large-scale user rating data. By leveraging the X-means algorithm, large-scale user evaluations are partitioned into clusters with homogeneous preferences, enabling efficient intra-cluster ranking via the TOPSIS method. A hybrid weighting mechanism, combining group size and information entropy, ensures balanced aggregation of rankings across clusters. The proposed dominance-non-dominance degree metric synthesizes global preferences, offering a robust solution for ranking 16 five-star hotels in London. Comparative analyses with traditional MADM methods demonstrate superior consistency (Kendall’s <span><math><mrow><mi>τ</mi><mo>=</mo><mn>0</mn><mo>.</mo><mn>983</mn></mrow></math></span>, Spearman’s <span><math><mrow><mi>ρ</mi><mo>=</mo><mn>0</mn><mo>.</mo><mn>997</mn></mrow></math></span>) and stability across diverse datasets. This framework not only streamlines decision-making for travelers but also provides actionable insights for hoteliers to refine service quality and market positioning.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"75 ","pages":"Article 101570"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841472","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}

{"title":"A reinforcement learning-driven framework for the Q-commerce multi-product unit scheduling problem","authors":"Weijian Zhang ,&nbsp;Min Kong ,&nbsp;Weimin Tan ,&nbsp;Yingxin Song ,&nbsp;Amir M. Fathollahi-Fard","doi":"10.1016/j.elerap.2025.101571","DOIUrl":"10.1016/j.elerap.2025.101571","url":null,"abstract":"<div><div>With the rapid emergence of Quick commerce (Q-commerce), e-commerce fulfillment systems are shifting from hour-level to minute-level responsiveness. However, this ultra-fast delivery mode introduces complex operational challenges such as multi-warehouse coordination, multi-stage processing, and high-frequency, small-batch order scheduling. To address these challenges, this study formulates and formally defines the Q-commerce multi-product unit scheduling problem with transportation and setup times, which systematically characterizes the outbound scheduling process under multi-resource collaboration. Given the problem’s strong NP-hard nature, a double Q-Learning-based variable neighborhood search (DQL-VNS) algorithm is developed. This algorithm integrates reinforcement learning with metaheuristic optimization to adaptively select neighborhood operators and adjust perturbation intensity, thereby enabling intelligent self-learning within complex search spaces. Extensive computational experiments show that DQL-VNS effectively reduces makespan and total tardiness. In large-scale instances, it achieves over a 10% reduction in average order delay compared with benchmark algorithms. Moreover, the results reveal that the multi-product unit decomposition strategy significantly enhances outbound efficiency and reduces tardiness. In terms of system configuration, the multi-warehouse-few-station mode outperforms the few-warehouse-multi-station mode by achieving better workload balance and greater fulfillment responsiveness. Additionally, due-date flexibility has a substantial impact on scheduling performance, emphasizing its critical role in maintaining customer satisfaction and delivery reliability. Overall, this study presents a novel modeling perspective and an intelligent optimization framework for outbound scheduling and resource coordination in Q-commerce, providing both theoretical and practical insights for developing responsive and sustainable instant retail logistics systems.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"75 ","pages":"Article 101571"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884652","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}

{"title":"Direct or agency? Manufacturer encroachment under platform’s data-driven marketing","authors":"Renji Duan ,&nbsp;Zhenzhong Guan ,&nbsp;Xinlan Ye ,&nbsp;Jianbiao Ren","doi":"10.1016/j.elerap.2025.101567","DOIUrl":"10.1016/j.elerap.2025.101567","url":null,"abstract":"<div><div>The development of e-commerce has enabled manufacturers to wholesale products to retail platforms, which then resell them to consumers. However, manufacturers may enter the end market by either establishing an independent official retail store (direct encroachment) or selling directly to consumers on the platform (agency encroachment). In response to the competitive pressure caused by such encroachment, the platform is motivated to invest in data-driven marketing (DDM) to enhance consumer purchasing utility. To this end, we analyse the interaction between the manufacturer’s encroachment strategy and the platform’s DDM decision using a game-theoretic model. The key results are as follows. First, the manufacturer prefers direct encroachment when the commission rate is high and selling cost is low, and agency encroachment when the commission rate is low. The decision depends on two opposing effects: the competition and expansion effects. Second, DDM is not always effective in deterring encroachment. Under certain conditions, DDM may instead induce the manufacturer to introduce a direct channel. Third, as the commission rate increases, the equilibrium outcome may evolve from “DDM + no encroachment” to “no DDM + agency encroachment”, and then back to “DDM + no encroachment”. Interestingly, during these transitions, the manufacturer’s (platform’s) profit increases (decreases) abruptly. Finally, we further explore six extensions and validate the robustness of our main conclusions.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"75 ","pages":"Article 101567"},"PeriodicalIF":6.3,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705615","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}