Venue2Vec: An Efficient Embedding Model for Fine-Grained User Location Prediction in Geo-Social Networks

Abstract

Geo-Social networks (GSN) significantly improve location-aware capability of services by offering geo-located content based on the huge volumes of data generated in the GSN. The problem of user location prediction based on user generated data in GSN has been extensively studied. However, existing studies are either concerning predicting users' next check-in location or predicting their future check-in location at a given time with coarse granularity. An unified model that can predict both scenarios with fine granularity is quite rare. Also, due to the heterogeneity of multiple factors associated with both locations and users, how to efficiently incorporate these information still remains challenging.Inspired by the recent success of word embedding in natural language processing, in this work, we propose a novel embedding model called Venue2Vec which automatically incorporates temporal-spatial context, semantic information, and sequential relations for fine-grained user location prediction. Locations of the same type, and those that are geographically close or often visited successively by users will be situated closer within the embedding space. Based on our proposed Venue2Vec model, we design techniques that allow for predicting a user's next checkin location, and also their future check-in location at a given time. We conduct experiments on three real-world GSN datasets to verify the performance of the proposed model. Experimental results on both tasks show that Venue2Vec model outperforms several state-of-the-art models on various evaluation metrics. Furthermore, we show how the Venue2Vec model can be more time efficient due to being parallelizable.

Perfilado inteligente de movilidad de usuarios

“…Al mismo tiempo, los dataset rara vez se dejan disponibles para la comunidad científica debido a los problemas de privacidad previamente mencionados. En este sentido, muchos autores han utilizado contenido público geo-localizado extraído de redes sociales, especialmente check-ins realizados por los usuarios [22] [23] [24]. Sin embargo, estos datos no son representativos, ya que no se puede conocer cuánto tiempo pasan los usuarios en cada lugar, además de que los usuarios normalmente omiten hacer check-ins en lugares cotidianos (como la casa o el trabajo) o embarazosos (como lugares de comida rápida) [25].…”

Geographic ratemaking with spatial embeddings

“…Early geographic representation models started with a specific application, then constructed representations useful for their applications. These include [Eisenstein et al, 2010, Cocos andCallison-Burch, 2017] for topical variation in text, [Yao et al, 2017] to predict land use, [Xu et al, 2020] for user location prediction, and [Jeawak et al, 2019, Yin et al, 2019 for geo-aware prediction. More recent approaches aim to create general geographic embeddings.…”

Geographic Ratemaking With Spatial Embeddings

“…Early geographic representation models started with a specific application and then constructed representations useful for their applications. These include Eisenstein et al (2010) and Cocos and Callison-Burch (2017) for topical variation in text, Yao et al (2017) to predict land use, Xu et al (2020) for user location prediction and Jeawak et al (2019) and Yin et al (2019) for geoaware prediction. More recent approaches aim to create general geographic embeddings.…”