This project explored whether is possible to track and comprehend thematic shifts in media attention through the automatic analysis of news articles. To do so, we analyzed how the Francophone media reported on food security issues over the past 8 years. More than 20,000 related articles published between 2004 and 2011 were selected using an ontology of food security-related terms. The contents of these articles were analyzed and organized into thematic clusters, which can be traced back to specific news articles or aggregated in a big picture representation. Semantic clustering methodologies and networks theory were used to automatically produce those clusters. The news items were also geo-located, enabling us to map how a given theme or issue is distributed worldwide. Moreover, themes identified at successive time steps were reconnected into streams of content. A stream visualization illustrates how topics are articulated through time.
An interactive online interface visualizes these maps, themes and news entries to answer questions such as: Is an issue – concerning, for example, the impact of climatic change on food security – attracting more attention with time? How does a specific issue relate to contiguous subjects (use of biofuel, for example)?
The interactive platform can be explored online at: http://pulseweb.veilledynamique.com
This short video below illustrates how it works:
Tubes with the same colour form hyper-streams of a common topic. The analysis shows that as the 2008 global economic crisis unfolded, news coverage shifted from a focus on humanitarian issues (red) to food price volatility (blue). In contrast, in 2011, the news focus shifted to social unrest (magenta).