News from newspapers, magazines, newswires and broadcast media deploy a crucial role in shaping the public opinion, informing the democratic process, and influencing markets and industry. The study of news media is a field of research for social scientists, however most of their work is performed manually. Our research is towards the automation of the analysis of news content by deploying state of the art methodologies from Machine Learning, Data Mining and Natural Language Processing. This has enabled us to analyse millions of articles from hundreds of news outlets and tens of languages. We detect emerging patterns and provide insights into the laws that influence the content of the media system. Key findings include: a mapping of factors that influence the stories that media choose to publish; the visualisation of the mediasphere; a measurement of levels of readability and subjectivity among different topics and the way they are presented in media; the ability to predict what stories will become popular. The significance of such large scale analyses is that they can lead to a data-driven approach to research in media studies in a similar way to biological and physical sciences.
Talk slides in pdf [~2,2MB]http://www.iit.demokritos.gr/docs/seminars/flaounas-slides.pdf