MPI-INF Logo
Campus Event Calendar

Event Entry

What and Who

Practical Extraction of Disaster-Relevant Information from Social Media

Shady Elbassuoni
American University Beirut
Talk
AG 5, RG1, MMCI  
AG Audience
English

Date, Time and Location

Friday, 20 June 2014
14:30
60 Minutes
E1 1 - Informatik
433
Saarbrücken

Abstract

During times of disasters online users generate a significant amount of data, some of which are extremely valuable for relief efforts. In this work, we study the nature of social-media content generated during two different natural disasters. We also train a set of models based on conditional random fields to extract valuable information from such content. We evaluate our extraction models over our two disaster-related datasets. We also evaluate our models over one non-disaster dataset to show that our extraction models are useful for extracting information from socially-generated content in general.

Contact

--email hidden
passcode not visible
logged in users only

Petra Schaaf, 06/16/2014 13:50 -- Created document.