PIKIPDL

Abstract

PurposeThe purpose of the paper is to conduct an exploratory study that proposes a personalized knowledge integration platform for digital libraries which can provide users with personalized information and knowledge services.Design/methodology/approachA prototype system (PIKIPDL) is designed and developed with two types of service, i.e. personalized information/knowledge service and personalized subject category service. Evaluation of the PIKIPDL by domain specialists and software experts is conducted. Comments are implications are addressed.FindingsThe main findings include the following: the proposed system can help suggest materials that readers are interested in for DL; the proposed system can help construct knowledge contents in a hierarchical structure; and a common recommendation concerning knowledge structure from the reviewers is that the proposed system should add a self‐organizing knowledge map function that would allow users to view knowledge subjects in a graphic manner.Practical implicationsThe results from the evaluation of reviewers revealed that the proposed PIKIPDL is acceptable to the integration of both personalized information service and personalized knowledge subject service. This implies that librarians and DL software agents should place emphasis on integrated service development to attract the attention of their users. Towards this goal, they could explain that personalized services (e.g. material recommendation, message recommendation, knowledge subject materials) with a mechanism of multi‐resource integration can help provide DL resources according to users' needs and wants, and in consequence to enhance DL service efficacy.Originality/valueThe research describes the importance of information/knowledge integration with respect to its support on the learning and study methods of users, and has developed a personalized knowledge integration platform as a mechanism that provides a personalized information service and a personalized knowledge subject category service. By employing Apriori algorithm and association rules as the data mining mechanism, personalized information recommendations are derived from circulation data, and a knowledge subject category is integrated from online sharing knowledge by participants.