Designing a personalized guide recommendation system to mitigate information overload in museum learning

Museum learning has received a lot of attention in recent years. Museum learning refers to people's use of museums to acquire knowledge. However, a problem with information overload has caused in engaging in such learning. Information overload signifies that users encounter a mass of information and need to determine whether certain information needs to be retained. In this paper, we proposed a personalized guide recommendation (PGR) system to mitigate this problem. The system used association rule mining to discover guide recommendation rules both from collective visiting behavior and individual visiting behavior, and then the rules were personalized. Using this system, visitors can obtain a PGR and avoid exposure to excessive exhibit information. To investigate user satisfaction with the PGR system, a user satisfaction questionnaire was developed to analyze the user satisfaction in a sample consisting of individuals of different genders and ages. The results showed that both men and women consistently accepted the PGR system and revealed that there were significant differences with regard to attitudes toward the system's service quality among different user ages. It was inferred that one possible reason for this was an effect related to users' prior experience with computers. A summary of the findings suggested that the PGR system generally obtained positive feedback.