Pioneering breakthrough in the study of media content
Friday, December 10, 2010
The study selected the top-ten news outlets - established by the volume of web traffic for each of the 27 EU countries
- Artificial intelligence techniques map news content
- More than one million news articles in 22 languages analysed
A breakthrough study has used artificial intelligence for the fist time to conduct a large-scale content analysis of multi-lingual texts across the European Union.
The research is a collaboration between project leader Nello Cristianini, Professor of Artificial Intelligence at the University of Bristol, Head of School Professor Justin Lewis of Cardiff University and an international research team.
The study set-out to pinpoint the factors that influence and shape the news agenda in the 27 European Union countries. Over 1.3 million articles were analysed, a sample size well beyond existing research techniques.
By using automated artificial intelligence methods and because of recent advances in machine translation and text analysis the research team discovered that chosen news content reflects national biases, as well as cultural, economic and geographic links between countries.
The research also found that outlets from countries that trade a lot with each other and are in the Eurozone were more likely to cover the same stories, as were countries, perhaps unsurprisingly, that vote for each other in the Eurovision song contest.
Asked about the significance of this new research technique, Professor Lewis said: “[It] has the potential to revolutionise the way we understand our media and information systems. It opens up the possibility of analysing the mediasphere on a global scale, using huge samples that traditional analytical techniques simply couldn’t countenance.”
Several expected connections between countries were found such as Greece-Cyprus; United Kingdom-Ireland; and Belgium-France.
Professor Lewis concluded: “While this approach lacks the analysis provided by people, this new research is a significant breakthrough in the study of media content due to the recent availability of millions of news articles in digital format.”
The paper, entitled The Structure of the EU Mediasphere, is published in the issue of Public Library of Science ONE (Dec. 2010).