Mining Conversations of Geographically Changing Users
2012 (English)In: Proceedings of the World Wide Web 2012 Workshop on Social Web for Disaster (SWDM2012), Lion, 2012Conference paper (Refereed)
In recent disaster events, social media has proven to be an effective communication tool for affected people. The corpus of messages contains valuable information about the situation on the ground, needs, and locations of victims. We propose a methodology to extract significant aspects of user discussions to better inform responders and enable an appropriate response.
The methodology combines location/movement based selection of user together with text mining (term frequency inverse document frequency) to identify important topics of conversation in a dynamic geographic network. We further suggest that both topics and movement patterns change during a disaster, which further allows for identification of new trends.
When applied to an area where a disaster has recently occured this approach can provide useful insights into where people are located, where they are going and what they saying during those movements.
Place, publisher, year, edition, pages
IdentifiersURN: urn:nbn:se:uu:diva-171589OAI: oai:DiVA.org:uu-171589DiVA: diva2:511653