A Dynamic Topic Model and Matrix Factorization-Based Travel Recommendation Method Exploiting Ubiquitous Data

The vast volumes of community-contributed geotagged photos (CCGPs) available on the Web can be utilized to make travel location recommendations. The sparsity of user location interactions makes it difficult to learn travel preferences, because a user usually visits only a limited number of travel 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 the evolving of topics and travel preferences. In this paper, we propose a dynamic topic model (DTM) and matrix factorization (MF)-based travel recommendation method. A DTM is used to obtain the temporally fine-grained topic distributions (i.e., implicit topic information) of users and locations. In addition, a large amount of explicit information is extracted from the metadata and visual contents of CCGPs, check-ins, and point of interest categories datasets. The information is used to obtain user–user and location–location similarity information, which is imposed as two regularization terms to constraint MF. The proposed method is evaluated on a publicly available Flickr dataset. Experimental results demonstrate that the proposed method can generate significantly superior recommendations compared to other state-of-the-art travel location recommendation studies.

[1]  John D. Lafferty,et al.  Dynamic topic models , 2006, ICML.

[2]  Hui Xiong,et al.  A General Geographical Probabilistic Factor Model for Point of Interest Recommendation , 2015, IEEE Transactions on Knowledge and Data Engineering.

[3]  Takahiro Hara,et al.  Mining people's trips from large scale geo-tagged photos , 2010, ACM Multimedia.

[4]  Martha Larson,et al.  Personalized Landmark Recommendation Based on Geotags from Photo Sharing Sites , 2011, ICWSM.

[5]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[6]  Tao Mei,et al.  Personalized Recommendation Combining User Interest and Social Circle , 2014, IEEE Transactions on Knowledge and Data Engineering.

[7]  Jiebo Luo,et al.  Diversified Trajectory Pattern Ranking in Geo-tagged Social Media , 2011, SDM.

[8]  Yun Zhang,et al.  The Spatial Analysis of Weibo Check-in Data - - The Case Study of Wuhan , 2013, GRMSE.

[9]  Xing Xie,et al.  Learning travel recommendations from user-generated GPS traces , 2011, TIST.

[10]  Adrian Popescu,et al.  Deducing trip related information from flickr , 2009, WWW '09.

[11]  Xiangyu Wang,et al.  Semantic-Based Location Recommendation With Multimodal Venue Semantics , 2015, IEEE Transactions on Multimedia.

[12]  Ling Chen,et al.  A system for mining interesting tourist locations and travel sequences from public geo-tagged photos , 2015, Data Knowl. Eng..

[13]  Thomas Hofmann,et al.  Collaborative filtering via gaussian probabilistic latent semantic analysis , 2003, SIGIR.

[14]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[15]  Mor Naaman,et al.  How flickr helps us make sense of the world: context and content in community-contributed media collections , 2007, ACM Multimedia.

[16]  Jimeng Sun,et al.  Dynamic Mixture Models for Multiple Time-Series , 2007, IJCAI.

[17]  Hong-Yuan Mark Liao,et al.  Personalized travel recommendation by mining people attributes from community-contributed photos , 2011, ACM Multimedia.

[18]  Tat-Seng Chua,et al.  Mining Travel Patterns from GPS-Tagged Photos , 2011, MMM.

[19]  Ling Chen,et al.  A context-aware personalized travel recommendation system based on geotagged social media data mining , 2013, Int. J. Geogr. Inf. Sci..

[20]  Tomoharu Iwata,et al.  Travel route recommendation using geotagged photos , 2012, Knowledge and Information Systems.

[21]  Chi-Yin Chow,et al.  Point-of-interest recommendations in location-based social networks , 2016, SIGSPACIAL.

[22]  Xing Xie,et al.  GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation , 2014, KDD.

[23]  Tat-Seng Chua,et al.  Research and applications on georeferenced multimedia: a survey , 2010, Multimedia Tools and Applications.

[24]  Xing Xie,et al.  Mining interesting locations and travel sequences from GPS trajectories , 2009, WWW '09.

[25]  Wei-Ying Ma,et al.  Recommending friends and locations based on individual location history , 2011, ACM Trans. Web.

[26]  Gang Chen,et al.  KISS: Knowing Camera Prototype System for Recognizing and Annotating Places-of-Interest , 2016, IEEE Transactions on Knowledge and Data Engineering.

[27]  Martha Larson,et al.  Nontrivial landmark recommendation using geotagged photos , 2013, TIST.

[28]  Panagiotis Symeonidis,et al.  A Graph-Based Taxonomy of Recommendation Algorithms and Systems in LBSNs , 2016, IEEE Transactions on Knowledge and Data Engineering.

[29]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[30]  Naonori Ueda,et al.  Topic Tracking Model for Analyzing Consumer Purchase Behavior , 2009, IJCAI.

[31]  Ling Chen,et al.  Topic based context-aware travel recommendation method exploiting geotagged photos , 2015, Neurocomputing.

[32]  Tat-Seng Chua,et al.  Mining Travel Patterns from Geotagged Photos , 2012, TIST.

[33]  Chi-Yin Chow,et al.  Spatiotemporal Sequential Influence Modeling for Location Recommendations , 2015, ACM Trans. Intell. Syst. Technol..

[34]  Jiawei Han,et al.  Geographical topic discovery and comparison , 2011, WWW.

[35]  Jiebo Luo,et al.  Geotagging in multimedia and computer vision—a survey , 2010, Multimedia Tools and Applications.

[36]  Wesam Elshamy,et al.  Continuous-time Infinite Dynamic Topic Models , 2013, ArXiv.

[37]  Huan Liu,et al.  Content-Aware Point of Interest Recommendation on Location-Based Social Networks , 2015, AAAI.

[38]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Analysis , 1999, UAI.

[39]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[40]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[41]  Slava Kisilevich,et al.  P-DBSCAN: a density based clustering algorithm for exploration and analysis of attractive areas using collections of geo-tagged photos , 2010, COM.Geo '10.

[42]  Tomoharu Iwata,et al.  Travel route recommendation using geotags in photo sharing sites , 2010, CIKM.

[43]  Peng Wang,et al.  Learning from contextual information of geo-tagged web photos to rank personalized tourism attractions , 2013, Neurocomputing.

[44]  Nadia Magnenat-Thalmann,et al.  Time-aware point-of-interest recommendation , 2013, SIGIR.

[45]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[46]  Chong Wang,et al.  Continuous Time Dynamic Topic Models , 2008, UAI.

[47]  Changhu Wang,et al.  Photo2Trip: generating travel routes from geo-tagged photos for trip planning , 2010, ACM Multimedia.

[48]  Marcel J. T. Reinders,et al.  Using flickr geotags to predict user travel behaviour , 2010, SIGIR.

[49]  Yan-Ying Chen,et al.  Travel Recommendation by Mining People Attributes and Travel Group Types From Community-Contributed Photos , 2013, IEEE Transactions on Multimedia.

[50]  Meina Song,et al.  TGTM: Temporal-Geographical Topic Model for Point-of-Interest Recommendation , 2016, DASFAA.