This work presents the design of a web mining system to understand the navigational behavior of passengers in developed Taiwan travel recommendation mobile app that provides four main functions including "recommend by location", "hot topic", "nearby scenic spots information", "my favorite" and 2650 scenic spots. To understand passenger navigational patterns, log data from actual cases of app were collected and analysed by web mining system. This system analysed 58981 sessions of 1326 users for the month of June, 2014. Sequential profiles for passenger navigational patterns were captured by applying sequence-based representation schemes in association with Markov models and enhanced K-mean clustering algorithms for sequence behavior mining cluster patterns. The navigational cycle, time, function numbers, and the depth and extent (range) of app were statistically analysed. The analysis results can be used improved the passengers' acceptance of app and help generate potential personalization recommendations for achieving an intelligent travel recommendation service.
Deng, Guang-Feng; Hung, Yu-Shiang; Yang, Chi-Ta; and Wu, Nien-Chu, "Web Usage Mining to Extract Knowledge for Modelling Users of Taiwan Travel Recommendation Mobile APP" (2014). ICEB 2014 Proceedings (Taipei, Taiwan). 4.