文献类型：期刊文献

英文题名：A hybrid ensemble learning method for tourist route recommendations based on geo-tagged social networks

作者：Wan, Lin[1];Hong, Yuming[1];Huang, Zhou[2];Peng, Xia[3];Li, Ran[4]

第一作者：Wan, Lin

通讯作者：Hong, YM[1]

机构：[1]China Univ Geosci, Fac Informat Engn, Wuhan, Hubei, Peoples R China;[2]Peking Univ, Inst Remote Sensing & GIS, Beijing, Peoples R China;[3]Beijing Union Univ, Inst Tourism, Beijing, Peoples R China;[4]Hubei Geol Environm Stn, Informat Ctr, Wuhan, Hubei, Peoples R China

第一机构：China Univ Geosci, Fac Informat Engn, Wuhan, Hubei, Peoples R China

通讯机构：[1]corresponding author), China Univ Geosci, Fac Informat Engn, Wuhan, Hubei, Peoples R China.

年份：2018

卷号：32

期号：11

起止页码：2225-2246

外文期刊名：INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE

收录：;Scopus(收录号：2-s2.0-85046417827);WOS:【SSCI(收录号:WOS:000443882300006)，SCI-EXPANDED(收录号:WOS:000443882300006)】；

基金：This work was funded by the National Natural Science Foundation of China [41401449], [41771425], [41501162], [41625003]; National Key Research and Development Program of China [2017YFB0503602], and Beijing Philosophy and Social Science Foundation [17JDGLB002].

语种：英文

外文关键词：Tour recommendations; spatial data mining; volunteered geographic information; location-based social networks; ensemble learning method

摘要：Geo-tagged travel photos on social networks often contain location data such as points of interest (POIs), and also users' travel preferences. In this paper, we propose a hybrid ensemble learning method, BAyes-Knn, that predicts personalized tourist routes for travelers by mining their geographical preferences from these location-tagged data. Our method trains two types of base classifiers to jointly predict the next travel destination: (1) The K-nearest neighbor (KNN) classifier quantifies users' location history, weather condition, temperature and seasonalityand uses a feature-weighted distance model to predict a user's personalized interests in an unvisited location. (2) A Bayes classifier introduces a smooth kernel function to estimate a-priori probabilities of features and then combines these probabilities to predict a user's latent interests in a location. All the outcomes from these subclassifiers are merged into one final prediction result by using the Borda count voting method. We evaluated our method on geo-tagged Flickr photos and Beijing weather data collected from 1 January 2005 to 1 July 2016. The results demonstrated that our ensemble approach outperformed 12 other baseline models. In addition, the results showed that our framework has better prediction accuracy than do context-aware significant travel-sequence-patterns recommendations and frequent travel-sequence patterns.