Search

Dynamically localizing users in online social networks is challenging because people seldom post location-related microblogs due to privacy concern. To increase inference accuracy, a promising approach is to leverage microblogs from friends. However, it is difficult because microblogs from friends may not be synchronized or informative. To tackle these challenges, we propose a system consisting two steps. Firstly, "co-location" friends are detected and used to infer the statistical locations of users. Secondly, users' dynamic locations are determined by considering both statistical locations and POI(point of interest) names in microblogs. Experiments based on real world dataset demonstrates that our approach outperforms previous studies.

Public bike-sharing systems (BSS) are booming all around the world, providing a flexible trip mode for people in cities. However, the imbalance usage among stations is causing problems for both system operators and users. As a first step to address this challenge, a recent paper has proposed a spatio-temporal bicycle mobility model based on historical bike-sharing data, and devised a traffic prediction mechanism on a per-station basis with sub-hour granularity. To better demonstrate the mobility model and prediction, we develop this data analysis and visualization system, not only presenting massive real-time prediction results but also serving as a platform for human mobility analysis.

As an innovative mobility strategy, public bike-sharing has grown dramatically worldwide. Though providing convenient, low-cost and environmental-friendly transportation, the unique features of bike-sharing systems give rise to problems to both users and operators. The primary issue among these problems is the uneven distribution of bicycles caused by the ever-changing usage and (available) supply. This bicycle imbalance issue necessitates efficient bike re-balancing strategies, which depends highly on bicycle mobility modeling and prediction. In this paper, for the first time, we propose a spatio-temporal bicycle mobility model based on historical bike-sharing data, and devise a traffic prediction mechanism on a per-station basis with sub-hour granularity. We extensively evaluated the performance of our design through a one-year dataset from the world's largest public bike-sharing system (BSS) with more than 2800 stations and over 103 million check in/out records. Evaluation results show an 85 percentile relative error of 0.6 for both check in and check out prediction. We believe this new mobility modeling and prediction approach can advance the bike re-balancing algorithm design and pave the way for the rapid deployment and adoption of bike-sharing systems across the globe.