Design and evaluate a mobile app for personalized library resource recommendations

Thesis Abstract

In an era characterized by an exponential growth of digital library resources, users increasingly face challenges in efficiently locating relevant materials amidst vast repositories, necessitating innovative solutions for personalized resource discovery. This study addresses the critical need for tailored library resource recommendations by designing and evaluating a mobile application aimed at enhancing user engagement and resource accessibility through personalization. The primary aim is to develop a user-centered mobile app that leverages machine learning algorithms to deliver individualized library resource suggestions, thereby improving information retrieval efficiency. Specific objectives include examining user preferences and behaviors, developing a recommendation system grounded in collaborative and content-based filtering techniques, and assessing user satisfaction and the system’s accuracy in resource suggestion through empirical testing. Employing a mixed-methods research design, the study combines quantitative and qualitative approaches to comprehensively evaluate the app's effectiveness. The quantitative phase involves a quasi-experimental pretest-posttest design with a sample of 300 university students selected through stratified random sampling, drawn from a university with a diverse student population. Data collection instruments consist of structured questionnaires measuring user satisfaction, perceived usefulness, and usability, alongside system logs analyzing interaction patterns and recommendation accuracy. The qualitative component comprises focus group discussions with a subset of 30 participants, aimed at exploring user experiences, expectations, and perceived value of the personalized recommendations. Data analysis employs descriptive statistics, paired-sample t-tests, and multiple regression analyses to evaluate the impact of the app on resource discovery efficiency, while thematic analysis is used to interpret qualitative feedback, thereby providing nuanced insights into user perceptions. The study anticipates that the personalized mobile app will significantly enhance the accuracy and relevance of resource recommendations, leading to increased user satisfaction, higher engagement levels, and improved scholarly information retrieval. It is expected that regression analysis will reveal a positive correlation between personalized recommendations and user perceived usefulness (p < 0.01), with usability scores indicating high acceptance and ease of use among participants. The qualitative findings are projected to highlight themes such as increased confidence in resource discovery, motivation to explore new materials, and appreciation for customized content delivery, which collectively affirm the value of personalized interfaces in academic contexts. This research contributes to the scholarly understanding of mobile-assisted information retrieval by integrating theoretical models such as the Unified Theory of Acceptance and Use of Technology (UTAUT) and the Information Foraging Theory, which underpin the system’s design and user interaction strategies. It advances current knowledge by providing an empirically validated model for personalized resource recommendations within mobile library contexts, emphasizing the importance of user-centered design and adaptive algorithms. Moreover, the study offers practical implications for library and information science professionals, including strategies for implementing effective recommendation systems, optimizing user interfaces, and fostering user acceptance of technological innovations in academic libraries. The main conclusion underscores the potential of mobile-based personalized recommendation systems to fundamentally improve resource discovery processes, thereby fostering more engaging, efficient, and user-centric library services. Based on the findings, recommendations include adopting adaptive recommendation frameworks tailored to specific user cohorts, enhancing system transparency and feedback mechanisms, and conducting longitudinal studies to assess long-term impacts on information literacy and resource utilization. Future research suggestions involve exploring integration with emerging technologies such as artificial intelligence and augmented reality to further personalize library experiences and extend the scope of user engagement in digital scholarly environments.