Purpose-of-Visit-Driven Semantic Similarity Analysis on Semantic Trajectories for Enhancing The Future Location Prediction

The number of people that are using or are even dependent on Location Based Services (LBS) is growing rapidly every year. In order to offer timely and user-tailored services, providers rely increasingly on forward-looking algorithms. For this reason, location prediction plays a key role in LBS. Recent approaches in location prediction leverage semantics in order to overcome drawbacks that characterise conventional non-semantic systems. However, when it comes to modelling locations, the majority of them constrain themselves to static semantical constructs and hierarchies, without taking the current situation, and most importantly, the users' varying personal perception into account. In this work, we introduce a novel dynamic approach that aims at taking the variation of the users' perception explicitly into consideration when describing locations, in order to elevate the overall prediction performance. For this purpose, we consider explicitly time and purpose of visit by building so called Purpose-of-Visit-Dependent Frames (PoVDF). Our framework is hybrid and combines both a data-driven, as well as a knowledge-driven model. To fuse these two models, we define a Purpose-of-Visit-Driven Semantic Similarity (PoVDSS) metric and use it as a fusing component between the two models. We conducted a user study to evaluate our approach on a real data set and compared it with two state of the art semantic and non-semantic algorithms. Our evaluation shows that our approach yields a location prediction accuracy of up to 80%.