Towards Social Event Detection and Contextualisation for Journalists

Abstract

Social media platforms have become an important source of information in course of a break- ing news event, such as natural calamity, political uproar, etc. News organisations and journal- ists are increasingly realising the value of information being propagated via social media. However, the sheer volume of the data produced on social media is overwhelming and manual inspection of this streaming data for finding, aggregation, and contextualising emerging event in a short time span is a day-to-day challenge by journalists and media organisations. It high- lights the need for better tools and methods to help them utilise this user generated information for news production. This paper addresses the above problem for journalists by proposing an event detection and contextualisation framework that receives an input stream of social media data and generates the likely events in the form of clusters along with a certain context.