IMPLEMENTATION OF DATA MINING IN DIGITAL LIBRARIES

Abstract

The development of information technology has driven a significant transformation in digital library systems, where the management and presentation of information now increasingly rely on the use of complex data. This study aims to examine the application of digital library techniques.data miningin analyzing and predicting user behavior to increase effectiveness personalized information retrieval in digital libraries. By using the approachnarrative reviewThis study identified and synthesized literature from various reputable databases such as Scopus, Web of Science, IEEE Xplore, and SpringerLink over the period 2010 - 2025. The results of the analysis indicate that the technique clustering, classification, association rules, and predictive modeling is the most commonly used method to understand user behavior patterns and build adaptive recommendation systems. The integration of these various algorithms has been shown to improve the relevance of information searches, user engagement, and satisfaction with digital library services. This study also highlights research gaps related to the limitations of empirical studies and methodological variations that hinder the generalizability of the results. Theoretically, this research contributes to the development of the concept of information seeking behavior and information systems success model, while practically providing direction for library managers in implementing data-driven strategies to improve service quality. Further research is recommended to explore the integration of data-driven techniques.artificial intelligence And machine learning, longitudinal evaluation of personalized retrieval, and implementation/cross-platform data mining in order to expand the effectiveness and reach of recommendation systems at the global level.