Developing a Framework and Wireframe for AI-Driven Personalization and Recommendation Systems in Library Management: A Design Thinking Approach
P. Arumugam, Singarayar Jayachristrayar, Rajendran Rega, Jesus Rayar · Journal of Web Librarianship · 2026
This research develops a framework and wireframes for an AI-driven personalization and recommendation system designed to enhance Library Management Systems (LMS). AI adapts library services dynamically to individual user characteristics and behaviors, such as reading preferences and interaction patterns, using predictive algorithms and behavioral analysis to deliver tailored recommendations. The study is primarily grounded in a User-Centered Design Thinking approach to ensure the system is intuitive, responsive, and meets diverse user needs. The proposed framework emphasizes seamless data integration and adaptive interface design. Prototypes created using Figma reflect intuitive, inclusive, and accessible features aligned with user needs. The prototype was evaluated in a controlled environment with high-frequency LMS users using the System Usability Scale (SUS) to assess usability and user satisfaction, achieving a score indicating excellent usability. Although the AI processing engine remains conceptual, this research provides a structured foundation for the future implementation of AI-driven recommendation systems in LMS, supporting enhanced user engagement and improved Selective Dissemination of Information through personalized and inclusive library experiences.