Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

作     者：Xiaoyu Sun Zhou Huang Xia Peng Yiran Chen Yu Liu 

作者机构：Institute of Remote Sensing and Geographical Information SystemsPeking UniversityBeijingPeople’s Republic of China Beijing Key Lab of Spatial Information Integration&Its ApplicationsPeking UniversityBeijingPeople’s Republic of China Collaborative Innovation Centre of eTourismTourism CollegeBeijing Union UniversityBeijingPeople’s Republic of China 

出 版 物：《International Journal of Digital Earth》 (国际数字地球学报（英文）)

年 卷 期：2019年第12卷第6期

页      面：661-678页

核心收录：

学科分类：080703[工学-动力机械及工程] 08[工学] 0807[工学-动力工程及工程热物理] 

基　　金：supported by grants from the National Key Research and Development Program of China[grant number 2017YFB0503602] the National Natural Science Foundation of China[grant number 41771425],[grant number 41625003],[grant number 41501162] the Beijing Philosophy and Social Science Foundation[grant number 17JDGLB002] 

主　　题：Recommendation system geotagged photos social media model-based approach support vector machine(SVM) gradient boosting regression tree(GBRT) 

摘      要：When travelling,people are accustomed to taking and uploading photos on social media websites,which has led to the accumulation of huge numbers of geotagged *** with multisource information(***,transportation,or textual information),these geotagged photos could help us in constructing user preference profiles at a high level of ***,using these geotagged photos,we built a personalised recommendation system to provide attraction recommendations that match a user’s ***,we retrieved a geotagged photo collection from the public API for Flickr(***)and fetched a large amount of other contextual information to rebuild a user’s travel *** then created a model-based recommendation method with a two-stage architecture that consists of candidate generation(the matching process)and candidate *** the matching process,we used a support vector machine model that was modified for multiclass classification to generate the candidate *** addition,we used a gradient boosting regression tree to score each candidate and rerank the ***,we evaluated our recommendation results with respect to accuracy and ranking *** with widely used memory-based methods,our proposed method performs significantly better in the cold-start situation and when mining‘long-tail’data.