With the increasing popularity of location-based services, such as tour guide and location-based social network, we now have accumulated many location data on the Web. In this paper, we show that, by using the location data based on GPS and users’ comments at various locations, we can discover interesting locations and possible activities that can be performed there for recommendations. Our research is highlighted in the following location-related queries in our daily life: 1) if we want to do something such as sightseeing or food-hunting in a large city such as Beijing, where should we go? 2) If we have already visited some places such as the Bird’s Nest building in Beijing’s Olympic park, what else can we do there? By using our system, for the first question, we can recommend her to visit a list of interesting locations such as Tiananmen Square, Bird’s Nest, etc. For the

GeoLife2.0 is a GPS-data-driven social networking service where people can share life experiences and connect to each other with their location histories. By mining people’s location history, GeoLife can measure the similarity between users and perform personalized friend recommendation for an individual. Later, we can predict the individual’s interest level in the locations visited by their friends while have not been found by them. The locations with relatively high interesting level can be recommended. Therefore, GeoLife2.0 can expand a user’s social network, provide them with a trustworthy resource matching their interests and help them sponsor georelated activities like cycling with minimal effort. 1.

People travel in the real world and leave their location history in a form of trajectories. These trajectories do not only connect locations in the physical world but also bridge the gap between people and locations. This paper introduces a social networking service, called GeoLife, which aims to understand trajectories, locations and users, and mine the correlation between users and locations in terms of usergenerated GPS trajectories. GeoLife offers three key applications scenarios: 1) sharing life experiences based on GPS trajectories; 2) generic travel recommendations, e.g., the top interesting locations, travel sequences among locations and travel experts in a given region; and 3) personalized friend and location recommendation. 1

The advance of GPS-enabled devices facilitates people to record their location histories with GPS traces, which imply human behaviors and preferences related to travel. In this paper, we perform two types of travel recommendations by mining multiple users ’ GPS traces. The first is a generic one that recommends a user with top interesting locations and travel sequences in a given geospatial region. Here, interesting locations mean the culturally important places, such as Tiananmen Square in Beijing, and frequented public areas, like shopping malls and restaurants. The second is a personalized recommendation that provides an individual with locations matching her travel preferences. To achieve the first recommendation, we model multiple users ’ location histories with a tree-based hierarchical graph (TBHG). Based on the TBHG, we propose a HITS (Hypertext Induced Topic Search)-based inference model, which regards an individual’s access on a location as a directed link from the user to that location. This model infers two values, the interest level of a location and a user’s travel experience, by taking into account 1) the mutual-reinforcement relation between the two values and 2) the geo-region conditions. Considering the inferred values, we mine the classical travel sequences among locations. In the personalized recommendation, we first understand the correlation among locations in terms of 1) the sequences that the locations have been visited and 2) the travel experiences of the persons accessing these locations. Beyond the geo-distance relation, this correlation represents the relation between locations in the

Social networks have evolved with the combination of geographical data, into Geo-social networks (GSNs). GSNs give users the opportunity, not only to communicate with each other, but also to share images, videos, locations, and activities. The latest developments in GSNs incorporate the usage of location tracking services, such as GPS to allow users to “check-in ” at various locations and record their experience. In particular, users submit ratings or personal comments for their location/activity. The vast amount of data that is being generated by users with GPS devices, such as mobile phones, needs efficient methods for its effective management. In this paper, we have implemented an online prototype system, called GeoSocial Recommender System, where users can get recommendations on friends, locations and activities. In order to provide recommendations, we represent this data by a 3-order tensor, on which latent semantic analysis and dimensionality reduction is performed using the Higher Order Singular Value Decomposition (HOSVD) technique. Also, as more data is accumulated to the system, we use incremental solutions to update our tensor. We perform an experimental evaluation of our method with a real data set and measure its effectiveness through recall/precision.

With the popularity of GPS equipped smartphone, large volumes of location data associated with mobile objects can be recorded anytime, anywhere. Extracting a user’s behavior patterns embedded helps us to tailor information feeds to better meet a user’s real needs with respect not only to spatio-temporal information but also to previous movement history. This research utilized the raw GPS readings in an attempt to generate semantically meaningful trajectory summaries by modeling individual movement pattern. One supervised movement pattern model for periodic daily routines and the other unsupervised one for all other activities were trained by knowledge-level features including Points of Interest, transportation mode and map-matched route. In addition, a familiarity index of routes was generated representing a user’s personal knowledge about the environment he/she lived in. i Acknowledgements I would like to thank my supervisor, William Mackaness, for his support and encouragement throughout the most different time of my project. I would also like to thank

Abstract. Location is a key element for ambient intelligence services. Due to GPS inaccuracies, inferring high level information (i.e., being at home, at work, in a restaurant) from geographic coordinates in still non trivial. In this paper we use information about activities being performed by the user to improve location recognition accuracy. Unlike traditional methods, relations between locations and activities are not extracted from training data but from an external commonsense knowledge base. Our approach maps location and activity labels to concepts organized within the ConceptNet network. Then, it verifies their commonsense proximity by implementing a bio-inspired greedy algorithm. Experimental results show a sharp increase in localization accuracy. 1

Abstract—With rapid growth of the GPS enabled mobile device, location-based online social network services become more and more popular, and allow their users to share life experiences with location information. In this paper, we considered a method for recommending places to a user based on spatial databases of location-based online social network services. We used a user-based collaborative filtering method to make a set of recommended places. In the proposed method, we calculate similarity of users ’ check-in activities not only their positions but also their semantics such as “shopping”, “eating”, “drinking”, and so forth. We empirically evaluated our method in a real database and found that it outperforms the naive singular value decomposition collaborative filtering recommendation by comparing the prediction accuracy. I.