[Back]


Talks and Poster Presentations (with Proceedings-Entry):

H. Huang:
"Context-Aware Location Recommendation Using Geotagged Photos in Social Media";
Talk: 12th International Conference on Location Based Services, Augsburg, Germany; 09-16-2015 - 09-18-2015; in: "Proceedings of 12th International Conference on Location Based Services", (2015), 2 pages.



English abstract:
Recently, the increasing availability of digital cameras and the rapid ad-vances in social media have led to the accumulation of a large number of geotagged photos, which may reflect people´s travel experiences in different cities, and can be used to generate location recommendations for tourists. Research on this aspect mainly focused on providing per-sonalized 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 behaviors.
This article explores context-aware methods to provide location recom-mendations matching a tourist's travel preferences and visiting context. Specifically, we apply clustering methods to detect touristic locations and extract travel histories from geotagged photos on Flickr. We then introduce a novel context similarity measure to quantify the similarity between any two contexts, and develop three context-aware collabora-tive filtering methods, i.e., contextual pre-filtering, post-filtering, and modeling. With these methods, location recommendations like `in simi-lar contexts, other tourists similar to you often visited ...´ can be provid-ed to the current tourist. Results of the evaluation with a publicly availa-ble Flickr photo collection show that these methods are able to provide a tourist with location recommendations matching his/her travel prefer-ences and visiting context. More importantly, compared to other state-of-the-art methods, the proposed methods can provide tourists with significantly better recommendations.
While Flickr data have been used in this study, these methods can also be applied to other kinds of travel histories, such as GPS trajectories and Foursquare check-ins, to provide context-aware recommendations.

Keywords:
geotagged photo, location recommendation, context-aware recommen-dation, collaborative filtering, trip planning

Created from the Publication Database of the Vienna University of Technology.