Title: Data mining for computational journalism
Authors: Verbeke, Mathias
Berendt, Bettina
d'Haenens, Leen
Opgenhaffen, Michaël
Issue Date: 18-Sep-2013
Conference: European Journalism Observatory (EJO) workshop location:Berlin, Germany date:18-19 September 2013
Abstract: Data mining is the computational process of discovering patterns in large amounts of data, and lies at the intersection of artificial intelligence, statistics and database systems. It has been one of the biggest success stories of Computer Science theory and applications in recent years. So far, Computational Journalism has hardly profited from this. It has taken cautious steps in adopting data journalism methods for data management and display, but lacks a principled approach for dealing with data complexity and news producers’ and consumers’ own roles for improving journalistic quality, and ultimately better informed citizens. Current research efforts in this direction have mainly neglected the dynamics of both network and information as well as the timeliness and updates of information, which are characteristic especially of the news domain. The aim of this proposal is to reduce the divide between the stakeholders in the media lifecycle (i.e. news organisations, journalists and citizens) that has been caused by the increasing amount of data and the new communication model offered by social media. By integrating techniques from data mining and social network analysis, we will provide a more inclusive framework for content creation and consumption.
Publication status: published
KU Leuven publication type: IMa
Appears in Collections:Faculty of Arts, Campus Sint-Andries Antwerp
Informatics Section
Institute for Media Studies
Faculty of Arts - miscellaneous

Files in This Item:

There are no files associated with this item.


All items in Lirias are protected by copyright, with all rights reserved.