Factors Influencing Behavioral Intentions of College Students in Smart Campus Face Recognition System in Chengdu
Z.M.Q. Li, Paitoon Porntrakoon, Liwei Chen · International Journal of Sociologies and Anthropologies Science Reviews · 2025
Background and Aim: The integration of face recognition systems with smart campuses improves the efficiency of identity authentication, attendance management, and access control, and realizes the modernization of education. However, factors such as personal privacy and data ethics affect college students' behavioral intentions and pose challenges to the successful adoption of these systems. This study aims to identify the key determinants that affect students' acceptance and use of smart campus face recognition systems and provide a decision-making basis for student information protection and university informatization promotion. Materials and Methods: A quantitative research design was adopted, focusing on seven key variables that influence behavioral intentions and usage behaviors. An online survey was conducted on 500 students from four colleges of Xihua University, and descriptive statistics were analyzed using frequency, percentage, mean, and standard deviation. Confirmatory factor analysis and structural equation modeling were used to analyze the data to assess the fit of the model and examine the relationship between variables. Results: The results showed that perceived usefulness, perceived ease of use, social influence, habit, risk belief, and trust belief had significant direct effects on behavioral intention. Perceived usefulness and risk belief emerged as the most important determinants of students' behavioral intention toward face recognition systems. Among them, students' risk beliefs hurt the behavioral intention of technology acceptance (β=-0.402, p < .001), which means that universities must reduce the perceived risk of the system; in addition, the trust belief and perceived usefulness of the system have a significant positive impact on the behavioral intention (β=0.279, p <0.001, β=0.234, p <0.001). Conclusion: The study emphasizes that universities need to prioritize the practicality and ease of use of facial recognition systems while addressing issues related to risk and trust, adopting security protocols and strict data protection policies in technology, and forming relevant safeguards laws, and regulations through multiple channels to alleviate concerns about olefins and enhance trust to increase the adoption rate of facial recognition systems and promote the in-depth application of technology in the digital transformation of education. These insights can also provide references for policy decisions and system design strategies, ultimately promoting smarter campus management and enhancing the decision-making process.