Nguyen Thi Hoi

Background: Generative Artificial Intelligence is increasingly transforming learning, work, and creative activities among young people. However, limited evidence explains how technological, social, behavioral, and individual factors jointly influence creativity in Generative Artificial Intelligence-assisted environments. Objective: This study examines the determinants of Generative Artificial Intelligence usage and their effects on youth creativity by integrating the Technology Acceptance Model 2 and the Componential Theory of Creativity. Methods: A quantitative survey was conducted with 400 young users who had prior experience with Generative Artificial Intelligence. Data were analyzed using Cronbach’s Alpha, Exploratory Factor Analysis, Confirmatory Factor Analysis, and Structural Equation Modeling. Results: The proposed model demonstrated excellent fit, with a chi-square to degrees-of-freedom ratio of 1.373, Comparative Fit Index of 0.981, Tucker-Lewis Index of 0.978, and Root Mean Square Error of Approximation of 0.031. Social influence and perceived usefulness significantly promoted habitual use, while technology trendiness and innate creativity positively influenced usage purpose. Usage purpose was the strongest predictor of creativity enhancement, followed by habitual use and innate creativity. The model explained 62% of the variance in creativity enhancement. Conclusion: Generative Artificial Intelligence serves not only as a productivity tool but also as a catalyst for youth creativity. The integration of the Technology Acceptance Model 2 and the Componential Theory of Creativity highlights how technological, social, behavioral, and individual factors jointly contribute to creativity enhancement, with practical implications for education, policy, and technology development. Keywords: GenAI, Creativity, TAM2, Componential Theory of Creativity, SEM

Background: Augmented reality (AR) has emerged as a transformative technology in e-commerce, enabling immersive, interactive, and personalized shopping experiences that help bridge the gap between online and offline retail environments. Although the adoption of AR has gained increasing attention in digital commerce, empirical evidence regarding the determinants of AR-enabled purchasing behavior remains limited, particularly among young consumers in emerging digital economies. Objective: This study aims to examine the factors that influence AR-enabled online purchasing decisions and identify the technological, psychological, social, and behavioral drivers that encourage consumers to adopt AR-supported shopping experiences. The proposed framework is illustrated through a survey conducted among young consumers in Hanoi, Vietnam, to provide empirical evidence. Methods: An integrated research framework was developed based on the TRA, TPB, UTAUT2, and social impact models. We employed a quantitative approach using data collected from 400 respondents who had prior experience using AR features in online shopping. SEM was applied to test the proposed hypotheses and evaluate the relationships among the constructs. Results: The findings indicate that Habit, Belief, Satisfaction, Social Influence, Facilitating Conditions, Perceived Number of Users, Subjective Norms, Effort Expectancy, and Attitude significantly influence consumers’ behavioral intention and purchase decision. In addition, BI serves as a significant mediating mechanism through which AR adoption factors are translated into actual purchasing behavior. Conclusion: By providing a comprehensive framework for understanding consumer adoption of AR technologies in online shopping environments, this study contributes to the growing literature on AR-enabled commerce. The findings offer practical implications for e-commerce platforms, digital retailers, and technology providers seeking to enhance customer engagement, trust, and purchase conversion through AR-enabled shopping experiences. The empirical evidence from Vietnam further enriches the understanding of AR adoption in emerging digital markets while supporting the proposed framework’s broader applicability across e-commerce contexts. Keywords: Augmented Reality, online purchasing decisions, young consumers, behavioral intention, digital commerce

This study presents a robust machine learning framework for image-based user feature classification on social media, with a particular emphasis on applications in e-commerce environments. To address the critical challenge of limited labeled data within large-scale and unstructured image repositories, the proposed approach integrates semi-supervised learning techniques to enhance model generalization and data utilization efficiency. Three widely adopted machine learning algorithms, Decision Tree, Random Forest, and Support Vector Machine (SVM), were systematically evaluated using K-fold cross-validation and standard performance metrics, including accuracy, precision, recall, and F1-score. Experimental results demonstrate that the Random Forest model outperforms other approaches, achieving an accuracy of 0.9468 and an F1-score of 0.9456, while maintaining strong computational efficiency and robustness. These findings underscore the effectiveness of ensemble learning methods in handling high-dimensional, imbalanced datasets. The proposed framework offers significant practical implications for user profiling, personalized recommendation systems, and targeted marketing strategies in modern digital ecosystems

The classification problem is crucial in business, providing an effective method for supporting search activities in areas such as e-commerce, education, and marketing. This has become especially important in the wake of the COVID-19 pandemic, which has increased the need to promote and stimulate domestic tourism. This research focuses on recommending tourist destinations based on historical search data related to domestic tourism. The study uses techniques like term frequency-inverse document frequency (TF-IDF) weight vector analysis and similarity measures to calculate recommendation scores. Data was collected from various tourism websites, covering destinations across all 63 provinces and cities in Vietnam. Experiments were conducted using three approaches: cosine similarity, the brute force algorithm, and long short-term memory (LSTM) for long-text processing. The results indicate that similarity-based methods produce recommendations that closely match user preferences. For full-sentence queries, the brute force algorithm delivers more accurate results, while LSTM provides faster processing times. These findings offer businesses multiple strategies for improving recommender systems in practical applications.

Discovering user's interests on social media was an issue that has received a lot of attention recently because it has high applicability in practice. The purpose of this paper is to introduce a method to detect user interest topics on social media by analyzing the content of user posts. In this paper, a semantic expansion technique based on Wikipedia and TF.IDF weighted vector representation, then estimated based on Pearson correlation. The result of the experiment shows that the method of topic detection can be applied to many different social media sites regardless of their structure, language, and links.