Yulong Gu

We Know Where You Are: Home Location Identification in Location-Based Social Networks

The rapid spread of smartphones has led to the increasing popularity of Location-Based Social Networks(LBSNs) like Foursquare, Gowalla, Facebook Places and so on where users can publish information about their current location. In LBSNs, identifying home locations of users is very important for various applications like effective location-based advertisement and recommendation. However, this problem is rather challenging because the location information in LBSNs is sparse and noisy: Only a small percentage of users share their home location information due to privacy concerns; users may check in at diverse places far from their home and make friends far away; many users even do not have any check-in information. In this paper, we propose a trust-based influence model, named as TSU to solve the problem. To be specific, TSU is a Trust-based unified probabilistic model that models edges in LBSNs based on signals from Social relationship data(social friendship, social trust) and User-centric data(check-in data) in LBSN. We proposed a Home Location Identification method based on TSU model and evaluate it on a large real-world LBSNs dataset. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art methods.

Fast Routing in Location-Based Social Networks Leveraging Check-in Data

With the extensive use of sensor-embedded smart phones, Location-Based Social Networks (LBSN) become more and more popular among online social networks in recent years. In social networks, constructing the shortest path with minimum cost between any two nodes efficiently is vital for both graph analysis and implementation of applications. This is well known as the routing problem in social networks. However, existing approaches of routing in social networks all fail in the scenario of LBSN which are large and dynamic. In this paper, we work out a fast routing system in LBSN leveraging check-in data to tackle this challenging problem. To be specific, firstly, we demonstrate the existence of the small world phenomenon in LBSN. Secondly, we reveal the friendship-inverse-geography property in LBSN. Thirdly, we design a Location-Based Fast Routing System LBFRS which can accomplish fast routing in LBSN leveraging geographical knowledge predicted from check-in data. Experiments on two real Location-Based Social Networks Go Walla and Bright kite have shown that LBFRS performs much more accurate prediction in geography than the baseline method and accomplishes dozens of times faster routing than Dijkstra in average.

Towards Accurate Relation Extraction from Wikipedia

Enormous efforts of human volunteers have made Wikipedia become a treasure of textual knowledge. Relation extraction that aims at extracting structured knowledge in the unstructured texts in Wikipedia is an appealing but quite challenging problem because its hard for machines to understand plain texts. Existing methods are not effective enough because they understand relation types in textual level without exploiting knowledge behind plain texts. In this paper, we propose a novel framework called Athena 2.0 leveraging Semantic Patterns which are patterns that can understand relation types in semantic level to solve this problem. Extensive experiments show that Athena 2.0 significantly outperforms existing methods.

HLGPS: A Home Location Global Positioning System in Location-Based Social Networks

The rapid spread of mobile internet and location-acquisition technologies have led to the increasing popularity of Location-Based Social Networks(LBSNs). Users in LBSNs can share their life by checking in at various venues at any time. In LBSNs, identifying home locations of users is significant for effective location-based services like personalized search, targeted advertisement, local recommendation and so on. In this paper, we propose a Home Location Global Positioning System called HLGPS to tackle with the home location identification problem in LBSNs. Firstly, HLGPS uses an influence model named as IME to model edges in LBSNs. Then HLGPS uses a global iteration algorithm based on IME model to position home location of users so that the joint probability of generating all the edges in LBSNs is maximum. Extensive experiments on a large real-world LBSN dataset demonstrate that HLGPS significantly outperforms state-of-the-art methods by 14.7%.

Relation Extraction from Wikipedia Leveraging Intrinsic Patterns

Enormous efforts of human volunteers have made Wikipedia become a treasure of textual knowledge. Relation extraction that aims at extracting structured knowledge in the unstructured texts in Wikipedia is an appealing but quite challenging problem because its hard for machines to understand plain texts. Existing methods are not effective enough because they understand relation types in textual level without exploiting knowledge behind plain texts. In this paper, we propose a novel framework called Athena leveraging Intrinsic Patterns which are patterns that can understand relation types in semantic level to solve this problem. Extensive experiments show that Athena significantly outperforms existing methods.

Context Aware Matrix Factorization for Event Recommendation in Event-Based Social Networks

Event-based Social Networks(EBSNs) which combine online interactions and offline events among users have experienced increased popularity and rapid growth recently. In EBSNs, event recommendation is significant for users due to the extremely large amount of events. However, the event recommendation problem is rather challenging because it faces a serious cold-start problem: Events have short life time and new events are registered by only a few users. Whats more, there are only implicit feedback information. Existing approaches like collaborative filtering methods are not suitable for this scenario. In this paper, we propose a Context Aware Matrix Factorization model called AlphaMF to tackle with the problem. Specifically, AlphaMF is a unified model that combines the Matrix Factorization model which models implicit feedbacks with the Linear contextual features model which models explicit contextual features. Extensive experiments on a large real-world EBSN dataset demonstrate that the AlphaMF model significantly outperforms state-of-the-art methods by 11%.

We Know What You Are Doing or Going to Do: Towards Accurate Human Activities Sensing

Understanding Activities of Human Daily Life is a fundamental and essential AI problem for Pervasive Computing and Human-Computer Interaction. Activity Sensing has attracted enormous research on activity recognition from mobile sensor data. However, there are two challenging problems: There is no standard taxonomy of activities and there is a lack of research on sensing high level activities. To this end, firstly, we built AHDL, the first knowledge base of Activities of Human Daily Life in this planet leveraging a large time use surveys. AHDL not only has a taxonomy of activities but also has common sense knowledge of these activities. Secondly, we designed ActivitySensor, a Conditional Random Fields based Sensor for sensing high level activities in AHDL. To be specific, ActivitySensor performs activity sensing using Conditional Random Fields model by combining contextual signals (time, location, previous activity and related person) and demographical signals. Extensive experiments demonstrated that ActivitySensor can improve the accuracy of activity recognition about 15% comparing to state-of-the-art methods on the same dataset. Whats more, we revealed that ActivitySensor can predict what will you do next with high accuracy.

Can Activities of Human Daily Life be Recognized and Predicted

Understanding Activities of Human Daily Life is a fundamental and essential AI problem for Ubiquitous Computing and Human-Computer Interaction. Activity inference has attracted enormous research on activity recognition from mobile sensor data. However, it is not clear how different signals can influence activity inference. To this end, we investigated the problem of activity recognition and prediction. Experiments showed that contextual signals like time, location, previous activity and related person are much more useful than demographical signals for activity recognition and prediction. We improved the accuracy of activity recognition by more than 15% comparing to existing work on the same dataset. Whats more, we revealed that we can predict what will you do next with high accuracy.