Location Based Services

LBS: Mobile Cartography

4110.2 - Context-Aware POI Recommendation in Location-Based Services

Tuesday, July 4
8:50 AM - 9:10 AM
Location: Coolidge

When visiting a new city, tourists often need help to effectively identify personally interesting locations (e.g., points of interest, POIs) from a potentially overwhelming set of choices. Trip planning is a time-consuming task. This task is further complicated by the physical environment, as personally interesting touristic locations may be scattered throughout a city. On the other hand, with the rapid advances in geotagged social media, recent years have witnessed many people publishing their travel information and experiences via social media, such as Foursquare check-ins and Flickr photos. Literature has shown that experiences from past users in similar contexts can help the current users to solve their problems efficiently, e.g., choosing where to visit. Therefore, aggregating geotagged social media data has a high potential in helping tourists identify locations of interest when visiting a new city. Research on this aspect mainly focused on providing personalized recommendations matching a tourist’s travel preferences, while ignored the context of visit (e.g., weather, season, and time of the day) that potentially influences his/her travel behavior.

This article explores context-aware methods to provide POI recommendations matching a tourist's travel preferences and visiting context. Specifically, we apply clustering methods to detect touristic locations (POIs) and extract travel histories from geotagged photos on Flickr. We then propose a novel context similarity measure to quantify the similarity between any two contexts, and develop three context-aware collaborative filtering methods, i.e., contextual pre-filtering, post-filtering, and modeling. With these methods, location recommendations like “in similar contexts, other tourists similar to you often visited …” can be provided to the current user. Results of the evaluation with a publicly available Flickr photo collection show that these methods are able to provide a tourist with POI recommendations matching his/her travel preferences and visiting context. More importantly, compared to other state-of-the-art methods, the proposed methods, which employ the introduced context similarity measure, can provide tourists with significantly better recommendations.

While Flickr data has been used in this study, these CaCF methods can also be extended for other kinds of travel histories, such as GPS trajectories and Foursquare check-ins, to provide context-aware recommendations

Haosheng Huang

Research Group Leader
University of Zürich

Dr. Haosheng Huang is a research group leader, and a senior researcher/lecturer at the GIScience Center of the Department of Geography at the University of Zurich, Switzerland. He is currently the Chair of the ICA Commission on Location-Based Services, and members of editorial board of the Journal of Location Based Services (Taylor & Francis), Open Geospatial Data, Software and Standards (Springer), and Journal of Geovisualization and Spatial Analysis (Springer).

Haosheng Huang's research interests lie in Geographic Information Science, particularly on Location-Based Services (LBS), Spatial Cognition and Computational Place Modelling.


Send Email for Haosheng Huang

Jukka M. Krisp

Applied Geoinformatics, Institute of Geography, University of Augsburg

Prof. Dr. Jukka M. Krisp, Professor of Applied Geoinformatics at the University of Augsburg. His research interests include Geovisualization and Location Based Services (LBSs).


Send Email for Jukka Krisp


4110.2 - Context-Aware POI Recommendation in Location-Based Services

Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for Context-Aware POI Recommendation in Location-Based Services