Semantic and geospatial mapping of instagram images in Saint-Petersburg
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific
|Title of host publication||Artificial Intelligence and Natural Language AINL FRUCT 2016 Conference|
|Publication status||Published - 2016|
|Publication type||B3 Non-refereed article in conference proceedings|
The availability of large urban social media data creates new opportunities for studying cities. In our paper we propose a new direction for this research: a joint analysis of geolocations of shared images and their content as determined by computer vision. To test our ideas, we use a dataset of 47,410 Instagram images shared in the city of St.Petersburg over one year. We show how a combination of semantic clustering, image recognition and geospatial analysis can detect important patterns related to both how people use a city and how they represent in social media.
- Artificial Intelligence, urban studies, Data science, computer science