https://elib.vku.udn.vn/handle/123456789/7679 2026-09-11T10:17:34Z https://elib.vku.udn.vn/handle/123456789/7757 Title: Boosting Test Smell Prediction using Deep Learning Authors: Huynh, Ngoc Khoa; Tang, Nhat Hung; Dang, Thien Binh; Nguyen, Thanh Binh Abstract: Test smells are indicative symptoms of poor design choices in test code, potentially reducing maintainability and compromising test effectiveness. While machine learning-based methods have been proposed to automate test smell detection, their predictive performance is still limited. Deep learning offers a promising solution due to its ability to learn complex context and patterns from data. However, its application to test smell prediction, particularly with sequence data extracted from test code, remains underexplored. To address these motivations, this study aims to present a deep learning-based approach for test smell prediction using input data in the form of sequences. The proposed method is experimentally evaluated on two popular test smells: Eager Test and Mystery Guest. The performance of all proposed models demonstrated significant improvement over baseline models, with the highest F1-score increase of approximately 24%. A comparative evaluation of three deep learning models, including Convolutional Neural Network, Bidirectional Long Short-Term Memory, and Gated Recurrent Unit, reveals that Bidirectional Long Short-Term Memory achieved the highest F1-score of 0.7475 for Eager Test, while Convolutional Neural Network performed best on Mystery Guest with F1-score of 0.6529. This work is considered the first effective application of deep learning for predicting test smell on sequence data, highlighting the promising approach in the area. Description: Information and Communication Technology (SOICT 2025); pp: 515-527 2026-09-01T00:00:00Z https://elib.vku.udn.vn/handle/123456789/7756 Title: The Influence of Digital Communication Activities on Brand Image and Brand Trust in Higher Education Institutions Authors: Le, Thi Hai Van Abstract: This study explores how digital communication activities impact brand image and brand trust within higher education institutions. Drawing on theories of branding, relationship marketing, and digital communication, the research proposes a model where Online Public Relations (E-PR), website communication, and social media communication shape brand image, which in turn affects brand trust. Data collected from university students were analyzed using reliability analysis, exploratory factor analysis, and regression analysis. The findings indicate that all three dimensions of digital communication positively influence brand image, and that brand image, in turn, significantly enhances brand trust. This study contributes to the existing literature on higher education branding and offers practical insights for universities aiming to improve their competitiveness in the digital age. Description: Research Inventy: International Journal of Engineering and Science; Vol.16, Issue 7; pp: 92-97 2026-07-01T00:00:00Z https://elib.vku.udn.vn/handle/123456789/7755 Title: The Psychological Mechanisms Underlying Digital Entrepreneurial Intentions and Behaviors in The Era of Artificial Intelligence: A Qualitative Synthesis Study Authors: Bui, Tran Huan; Dinh, Nguyen Khanh Phuong Abstract: In the context of global digital transformation, the integration of Artificial Intelligence (AI), particularly Generative Artificial Intelligence (GAI), has fundamentally redefined the developmental trajectory of digital entrepreneurs. This paper conducts a qualitative synthesis study to explore the underlying psychological mechanisms that drive entrepreneurial intentions and behaviors in the AI era. Drawing upon evidence from 44 academic sources, the study elucidates the role of AI as a powerful technological stimulus within the Stimulus–Organism–Response (SOR) framework. The findings reveal that AI adoption, exemplified by technologies such as ChatGPT, represents not merely a technological shift but also a transformative force that profoundly influences entrepreneurial identity aspiration and digital entrepreneurial self-efficacy (ESE). The study establishes a psychological transmission pathway through which AI literacy and digital capabilities enhance perceptions of entrepreneurial attractiveness and feasibility, thereby fostering entrepreneurial hustle and proactive venture creation behaviors. Furthermore, the paper examines critical barriers associated with technology anxiety and the phenomenon of cognitive offloading, both of which may hinder effective entrepreneurial decision-making and long-term capability development. Based on these findings, the study proposes educational and training strategies aimed at balancing echnical competence with psychological adaptability in order to cultivate a resilient and future-ready generation of digital entrepreneurs. Description: Research Inventy: International Journal of Engineering and Science; Vol.16, Issue 7; pp: 87-91 2026-07-01T00:00:00Z https://elib.vku.udn.vn/handle/123456789/7754 Title: AI-Driven Business Model Transformation and Risk Management for Micro-Firms: A Qualitative Synthesis Study Authors: Bui, Tran Huan; Dinh, Nguyen Khanh Phuong Abstract: Micro-firms, defined as businesses employing fewer than ten employees, constitute the backbone of the global economy. Nevertheless, they frequently encounter severe resource constraints and elevated operational risks. This study conducts a qualitative synthesis to examine how Artificial Intelligence (AI), particularly Generative Artificial Intelligence (GenAI), facilitates business model transformation and enhances risk management within this segment. Drawing upon 44 academic sources, the study adopts the Technology Organization–Environment (TOE) framework to identify the key drivers and barriers influencing AI adoption. The findings indicate that AI functions as a capability-leveling mechanism, enabling micro-firms to perform sophisticated activities such as predictive analytics and process automation at relatively low cost. The study further demonstrates AI’s role in the early detection of financial distress signals and the reduction of human error. However, challenges related to data quality and implementation costs remain significant obstacles. The paper proposes a human–AI symbiotic risk management framework and highlights the need for targeted policy interventions aimed at narrowing the digital divide faced by vulnerable enterprises. Description: Research Inventy: International Journal of Engineering and Science; Vol.16, Issue 7; pp: 83-86 2026-07-01T00:00:00Z