A Multi-granularity Decade-Long Geo-Tagged Twitter Dataset for Spatial Computing

The widespread use of social media platforms has led to the generation of a huge amount of geo-tagged information embedded within user-generated content. This data holds significant potential for location-aware applications and location-based services. However, the spatial computing community still lacks access to a comprehensive, large-scale social media dataset that spans extensive regions and encompasses multiple levels of location granularity over an extended period. In this research paper, we present a geo-tagged Twitter dataset comprising tweets from over 100 countries spanning a period of more than 10 years. The dataset includes four levels of location granularity: country, state/province, city, and neighboring regions. Additionally, we categorize locations into two types: user profile locations and tweet locations.

Search by Tweet Location


Filter by Country Code

Filter by Language Code