Authors: Yihong Yuan*, , Yongmei Lu, Texas State University, Yu Liu, Peking University, Edwin T. Chow, Texas State University
Topics: Geographic Information Science and Systems, Urban Geography
Keywords: Location-based social media, data quality, smart city services
Session Type: Paper
Start / End Time: 1:10 PM / 2:50 PM
Room: Coolidge, Marriott, Mezzanine Level
Presentation File: No File Uploaded
In recent decades, Social Network Sites (SNS), such as Facebook and Twitter, have attracted users worldwide by providing a means to communicate and share their daily lives. Meanwhile, the wide spread use of smart phones, which are equipped with sensors that allow users to instantly locate themselves, has brought another crucial aspect to this development: location. Previous studies have used location-based social media (LBSM) as potential resources to characterize social perceptions of place and model human activities in various smart city applications.
However, similar to other types of big (geo) data, LBSM data may have critical sampling biases. If LBSM data are applied to decision-making in smart city services, such as emergency response or transportation, it is essential to understand the biases of such data in order to justify policies or management practices. This study aims to examine the biases of LBSM data from various perspectives, including but not limited to those of spatial, temporal, sociodemographic, and semantic. A series of empirical cases will be provided to support the examination of such biases and their impacts on smart city applications. This paper will further discuss the strategies to improve the efficiency of LBSM data in smart city services through incorporating different public data. The results will provide valuable inputs for understanding how LBSM biases manifest themselves in various applications in urban planning and policymaking.