CARDIFF U. (UK) — News outlets in Europe choose daily content based on national biases, and cultural, economic, and geographic links between countries, a new analysis finds.
An international team of researchers recently conducted the first large-scale content analysis of multilingual texts using artificial intelligence techniques—automated smart computing.
While each news outlet may make news choices based on individual criteria, clear patterns emerged when researchers studied choices across outlets over a long period of time.
The researchers analyzed more than one million news articles in 22 languages to pinpoint factors that influence and shape the news agenda in 27 European countries.
By using automated methods from artificial intelligence and because of recent advances in machine translation and text analysis the team was able to analyze 1,370,874 articles—a sample size well beyond existing research techniques.
Outlets from countries that have substantial trade with each other and are in the Eurozone are more likely to cover the same stories, as are countries that vote for each other in the Eurovision song contest.
Deviation from ‘normal content’ is more pronounced in outlets of countries that do not share the Euro, or have joined the European Union later.
The findings are reported in PLos One.
“This approach has the potential to revolutionize the way we understand our media and information systems,” says Justin Lewis, professor of journalism, media, and cultural studies at Cardiff University.
“It opens up the possibility of analyzing the mediasphere on a global scale, using huge samples that traditional analytical techniques simply couldn’t countenance. It also allows us to use automated means to identify clusters and patterns of content, allowing us to reach a new level of objectivity in our analysis.”
“Automating the analysis of news content could have significant applications, due to the central role played by the news media in providing the information that people use to make sense of the world,” says Nello Cristianini, professor of artificial intelligence at the University of Bristol.
The researchers selected the top-ten news outlets—established by the volume of Web traffic to either its leading news feed or main page—for each of the 27 EU countries.
They gathered their sample from the top stories of these outlets for six months, from Aug. 1, 2009 until Jan. 31, 2010. The non-English language news items, which totaled 1.2 million, were translated automatically to English.
Several expected connections between countries were found: Greece-Cyprus; Czech Republic-Slovakia; Latvia-Estonia; United Kingdom-Ireland; and Belgium-France.
Links between countries not explained by borders, trade or cultural relations, could be due to other factors and may form the basis of further research.
“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,” adds Lewis.
More news from Cardiff University: www.cardiff.ac.uk/news/