With the advancement of Internet technology and the widespread use of mobile smartphones, urban e-commerce is becoming increasingly saturated. Rural e-commerce ushered in a new era of development. How to improve rural logistics carrying capacity to keep up with the development of rural e-commerce and better serve the development of rural e-commerce has become a hot topic. The purpose of this study is to predict logistics demand in the context of the development of rural e-commerce. We develop an indicator system for forecasting rural logistics demand in Guangdong Province. The GM (1,1) gray forecasting model with a weakening buffer operator was used to forecast rural logistics demand in Guangdong Province. According to the results, the prediction model has good matching and precision. It was also found that demand for rural logistics in Guangdong Province will generally rise in the short to medium term. Based on the findings of this study, the government should stimulate demand for rural consumer goods, encourage technological innovation, develop an Internet-rural logistics mode, and meet the supply requirements of rural logistics based on the situation of each region.

Rural e-commerce entrepreneurship education (EE) in Higher Education Institutions (HEIs) can effectively enhance the development of the rural e-commerce industry and improve the motivation of students to start or be employed in rural e-commerce, but how to conduct effective evaluation is an issue that remains to be clarified. The research objectives of this paper are as follows: to establish a “student-centered” evaluation model for EE in HEIs, to integrate rural e-commerce professional education with EE, and to provide practical guidance for the evaluated HEIs. This paper constructs an evaluation model of rural e-commerce EE in HEIs. The research method combines Analytic Hierarchy Process (AHP) and Fuzzy Comprehensive Evaluation Method. The questionnaire method was used to obtain 384 valid data for the empirical analysis of the education of the Software Engineering Institute of Guangzhou. The study’s results found that the final evaluation result of the school’s rural e-commerce EE grade was good. The indicators at the level of educational support and feedback effectiveness scored relatively high, but those at the level of learning input and educational process scored low. Based on the findings, recommendations were made in terms of developing more open feedback channels, providing a full range of services, and social flexibility of the training program.

In the context of ongoing curriculum teaching reform accelerated by the COVID-19 pandemic, evaluating online logistics courses from the learners’ perspectives and identifying strategies for improvement have become critical areas of inquiry. Despite the growing body of literature on online education, existing studies often overlook the specific topics of interest and emotional tendencies of online logistics course learners. This study addresses this gap by utilizing the push-pull-mooring (PPM) theory, originally developed for human migration studies, to elucidate the transition of learners from offline to online environments, while exploring the formation process and significance of online logistics course instruction. We employ the ROST Content Mining System (ROST CM) software to conduct word frequency analysis, semantic network analysis, and sentiment analysis on review text data from two logistics courses offered on the China University massive open online courses (MOOC) platform. Our findings indicate that online learners prioritize three key aspects: “teacher,”“course,” and “learning content,” with high-frequency words revealing a hierarchical structure of “topic → transition → emotion.” While most learners expressed positive and satisfactory sentiments, a minority conveyed neutral or negative emotions. Based on these insights, this paper proposes targeted recommendations focusing on instructor guidance, enhancing online interaction, and fostering reflective teaching practices.

Consumer satisfaction in automotive spare parts e-commerce is shaped by multidimensional factors that are difficult to quantify through conventional survey methods. This paper presents an intelligent text mining framework that integrates multiple machine learning and natural language processing techniques to systematically extract and analyze consumer sentiment from 1,236 validated Taobao reviews. Specifically, TF-IDF (Term Frequency-Inverse Document Frequency) is employed for discriminative keyword extraction, semantic network analysis is applied to model inter-word relational structures, and LDA (Latent Dirichlet Allocation) topic modeling is used to discover latent thematic patterns, identifying four core satisfaction dimensions: Logistics, Quality, Price, and Customer Service. For sentiment quantification, a domain-adaptive SnowNLP model based on the Naive Bayes algorithm is fine-tuned on a domain-specific automotive e-commerce corpus, achieving an accuracy improvement from 11.4% to 83.1%. Additionally, a domain-specific sentiment lexicon is constructed via the SO-PMI (Semantic Orientation-Pointwise Mutual Information) method to enhance lexicon-level sentiment scoring. The integrated intelligent analysis reveals that positive sentiment is predominantly driven by logistics efficiency and product reliability, while negative sentiment concentrates on installation complexity and service knowledge deficiencies. The proposed system provides an automated, domain-adaptable intelligent pipeline for e-commerce opinion mining, with demonstrated applicability to the automotive spare parts domain, offering data-driven decision support for product optimization and service quality improvement.

Although monetization has been widely discussed in digital games, less attention has been paid to how it is discussed in narrative-centered Interactive Full-Motion Video (FMV) Games, where user experience depends heavily on continuity, completeness, and emotional engagement. Addressing this gap, this study analyzes 8676 Steam user reviews of Road to Empress I using NLP-based preprocessing, semantic analysis, sentiment analysis, and LDA topic modeling. The results indicate that the review corpus was organized around several interconnected dimensions, including narrative progression, character engagement, audiovisual performance, interactivity, and payment structure, with narrative-related concerns occupying a central position. Compared with the full corpus, the identified monetization-related review subset showed a less positive sentiment distribution, suggesting that monetization-related discussion within this subset was associated with more negative evaluations. Topic modeling further indicated three prominent concerns: interrupted narrative continuity, perceived incompleteness, and dissatisfaction with value for money. Overall, the findings suggest that, within the identified subset, monetization was discussed not merely as a pricing issue, but as part of the broader experiential structure through which continuity, completeness, and value were judged. The study contributes to research on Interactive FMV Games by foregrounding monetization as an experiential dimension and offers practical implications for designing less disruptive monetization strategies in narrative-centered interactive products.

Generative AI (AIGC) and multimodal digital avatars are reshaping live-streaming e-commerce, yet limited research has systematically examined how consumers perceive the interactive characteristics of AI digital anchors and how such perceptions influence behavioral outcomes.Grounded in the Stimulus-Organism-Response (SOR) framework, this study examines how the interactive characteristics of AI digital anchors influence consumers’ purchase intention. We conceptualize these characteristics along three dimensions: interactive responsiveness, personalized service capability, and appearance attractiveness. Based on 240 valid survey responses, the results show that all three dimensions positively affect purchase intention. Emotional response and perceived trust serve as both independent and serial mediators. In addition, viewing frequency selectively strengthens the effect of personalized service capability, while the effects of responsiveness and appearance attractiveness remain relatively stable across users. To complement the regression analysis, this study further applies Random Forest and SHAP. The machine learning results show that all three predictors contribute meaningfully to purchase intention, with appearance attractiveness showing slightly higher predictive importance and greater heterogeneity across individuals. By linking AI system characteristics to user perceptions and behavioral outcomes, this study enriches HCI research on embodied intelligent agents in e-commerce and offers practical insights for the design of AI digital anchors.