Mining User Check-in Behaviors in Location-Based Social Networks for Point-of-Interest Recommendation

• Main Authors: Wen-NingKuo, 郭雯寧
• Other Authors: Vincent S. Tseng
• Format: Others
• Language: en_US
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/49421326555800973901

碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 100 === In this thesis, we propose a novel approach named Urban POI Mine (UPOI-Mine) that integrates location-based social network (LBSN) for recommending users urban POIs based on the user preferences and location properties simultaneously. The core idea of UPOI-Mine is to build a regression-tree-based predictor in the normalized check-in space so as to support the prediction of interestingness of POI related to each user’s preference. Based on the LBSN data, we extract the features of places from i) Social Factor (SF), which is summarized from all socially similar users’ check-ins at a specific POI for each user; ii) Individual Preference (IP), which indicates the probability of checking in a POI related to the semantic tag between the user and POI; and iii) POI Popularity (PP), which is derived by measuring relative popularity of individual POI. To our best knowledge, this is the first work on urban POI recommendation that considers social factor, individual preference and POI popularity in LBSN data simultaneously. Through a series of experiments on a real dataset, we have validated our proposed UPOI-Mine and shown that UPOI-Mine has excellent performance under various conditions.