Using adaptive resonance theory and data-mining techniques for materials recommendation based on the e-library environment

Purpose - The purpose of this research is to illustrate the use of artificial neural network (ANN) and data-mining (DM) technologies as a good approach for satisfying the requirements of library users. Design/methodology/approach - This research presents the Intelligent Library Materials Recommendations System (ILMRS) which uses the adaptive resonance theory (ART) network to distribute readers into different clusters according to their personal background. When clusters of related personal background have been established, the Apriori algorithm is used to discover the suitable materials in which readers are interested and which they may need. Findings - The investigation results indicate that the ART and Apriori mining techniques can be used to improve the accuracy of the recommendations for reading materials in the library. Moreover, readers can be divided by means of demographic variables into three segments. Finally, the questionnaire survey proved that the proposed recommender system will be a suitable approach for stimulating the readers' motivation and interest. Research limitations/implications - This research is limited by its datasets from a digital library of a university in Taiwan, and it is applied by ART and Apriori mining techniques to recommend materials of readers. Originality/value - Today, digital information is becoming ever more popular. The huge quantity and the diversity of digital information are its main features. Therefore, readers are interested in obtaining useful information in an efficient manner. In this research, a digital library can use this approach to anticipate a reader's needs in advance based on the mining results.