Geographic information, texts and social media



Davide Buscaldi

Geographic information, texts and social media
Speaker:
Davide Buscaldi
Short Bio:
Davide Buscaldi is Maître de conférences, LIPN, Université Paris 13. He got his Ph.D. “cum laude" in Pattern Recognition and Artificial Intelligence at the Universidad Politécnic de Valencia in 2010 with a thesis on “Toponym Disambiguation in Information Retrieval". He joined Université Paris 13 after a post-doc at IRIT of Toulouse (France) on semantic IR. His main research interests are in the fields of Natural Language Processing, Machine Learning and Information Retrieval and he is currently working on geographic IR, word sense disambiguation, ontology learning and population, Question Answering, sentiment and opinion mining.
Abstract:
During the last 20 years, many researchers have proposed various techniques to improve the retrieval of geographic information by means of spatial analysis, filtering and reclassification according to the toponyms identified in the text. Some estimates indicate that at least 70% of the information contained in online texts contains geographical information, often in the form of place names. Today, the decline of the blogosphere and the success of social media in a connected society make geographic information even more important, at the centre of key events such as weather, natural disasters, social movements, sporting events and more. Extracting and analyzing geographic information in these contexts presents interesting challenges that will be the focus of this presentation.
Date:
Wednesday, May 9th, 2018 - 15.00
Location:
DIBRIS, Valletta Puggia, Room 711

 

Sei qui: Home Ricerca Seminari di ricerca Geographic information, texts and social media