文章基本信息

标题：A Survey on a New Approach to Travel Recommendation Using Dynamic Topic Model and Matrix Factorization Based
本地全文：下载
作者：Harshvardhan Hanmnatrao Patil ; Prof. S.D. Satav
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：12
页码：16932
DOI：10.15680/IJIRCCE.2017.0512026
出版社：S&S Publications
摘要：On web the rapid growth of online travel information has to face for tourists who have to choose from alarge number of travel available packages to satisfy their personalized requirements to travel. The sparsity of userlocationinteractions makes it difficult to learn travel preferences, because a user usually visits only a limited number oftravel locations. Static topic models can be used to solve the sparsity problem by considering user travel topics.However, all travel histories of a user are regarded as one document drawn from a set of static topics, ignoring theevolving of topics and travel preferences. In this paper, we propose a dynamic topic model (DTM) and matrixfactorization (MF) based travel recommendation method. A DTM is used to obtain the temporally fine-grained topicdistributions (i.e., implicit topic information) of users and locations. In addition, a large amount of explicit informationis extracted from the metadata and visual contents of CCGPs, Check-ins, and POI categories datasets. The informationis used to obtain user-user and location-location similarity information, which is imposed as two regularization terms toconstraint MF. User can view recommended places route on map.
关键词：Travel recommendation; geo-tagged photos; social media; multimedia information retrieval; check-in;record; dynamic topic model; travel recommendation.