Contextualized Relevance Evaluation of Geographic Information for Mobile Users in Location-Based Social Networks

ISPRS International Journal of Geo-Information

Ming Li¹  Yeran Sun²  Hongchao Fan²  Norbert Bartelme² 

[1] GIScience Research Group, Institute of Geography, Heidelberg University, Heidelberg 69120, Germany;

关键词: contextualization;    geographic relevance;    location-based social networks;    mobility pattern;   

DOI  :  10.3390/ijgi4020799

来源: mdpi

【 摘 要 】

The relevance of geographic information to mobile users must be evaluated by taking into account the usage context. This paper assumes that emerging Location-based Social Networks (LBSNs) contain contextual information rich enough to be used in order to contextualize such an evaluation process. This assumption is demonstrated through an exploratory analysis of a Foursquare check-in dataset, which reveals the impacts of two contextual factors—temporal and spatial—on mobility patterns. This paper then proposes an approach that may be used to contextualize the evaluation of geographic information’s relevance. The proposed algorithm links a priori relevance to the contextualized relevance using the hidden impacts of contextual factors. Improved performance from the experiments carried out confirms the validity of the proposed approach, as well as the benefits of utilizing contextual information within the relevance evaluation process.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.