|
|
 |
|
Lundi 28 Novembre
| Heure: |
14:00 - 15:00 |
| Lieu: |
Salle B107, bâtiment B, Université de Villetaneuse |
| Résumé: |
Semantically enriched methods for next generation microblog message fine-grained geolocalization |
| Description: |
Laura Di Rocco Consistent user-generated data represent a valuable source for the extraction of new types of information patterns and knowledge. The multifaceted nature of user-generated data, along with its geographic component, is being exploited to better understand social dynamics and propagation of information. Social media activities can be associated with both an explicit and an implicit geographic information component. Consider, for instance, Twitter as a typical example. In this case, georeferencing information can be explicitly available as metadata, such as the user profile location and the GPS coordinates of the device from which the activity is performed. By contrast, implicit georeferencing information can be inferred, with variable degree of confidence, by the message content itself, which may contain images, names of entities with known spatial location, or by the social relationships and interactions among users.
Our focus is on inferring the tweeting location (i.e., the position of the user when the tweet was sent) rather than the user home location. Since explicit tagging is used only in a small percentage of tweets, we will use geospatial information implicit in the messages to improve the resolution of the georeferencing process. With the aim of fully exploiting the (explicit and implicit) fine-grained georeferencing information made available by social media, the project relies on semantically enhanced and refined crowdsourced geospatial data to extract fine-grained implicit geoinformation contained in tweet contents.
Short Bio:
Laura Di Rocco is a PhD Student at University of Genoa and a visiting PhD Student at Paris Descartes University (LIPADE). Her research interests are in the areas of geospatial data and text mining on social media. |
|
|
