Massive-Scale Data Mining to Enhance Digital Library with Applications in College Education

Area of Science:

• Information Science
• Computer Science
• Human-Computer Interaction

Background:

• Digital libraries face information overload, necessitating a shift from user-initiated searches to proactive information delivery.
• Personalized services and intelligent recommendation systems are crucial for modern digital library development.
• Effective data mining and exploration technologies are key to optimizing digital library services.

Purpose of the Study:

• To construct a theoretical model explaining the factors influencing user satisfaction with intelligent information recommendation services in digital libraries.
• To investigate the impact of data mining, recommendation quality, and service delivery on user satisfaction.
• To provide insights for optimizing digital library services in the era of information abundance.

Main Methods:

• Grounded theory approach involving coding and analysis of interview data.
• Extraction of initial concepts, basic categories, and main categories.
• Development of a theoretical model based on identified relationships and mechanisms.

Main Results:

• User preference moderates the influence of system quality, recommendation quality, service quality, and recommendation format on satisfaction.
• Data mining system quality, recommendation information quality, recommendation service quality, and recommendation form significantly impact user satisfaction.
• A theoretical model was constructed to illustrate these influence mechanisms.

Conclusions:

• Intelligent information recommendation services are vital for digital library user satisfaction.
• Optimizing data mining, recommendation content, service delivery, and format is essential for enhancing user experience.
• Digital libraries are evolving into dynamic environments supporting the entire information lifecycle, from creation to knowledge dissemination.