This new application based on IDIOM technology tracks the candidates’ performance on the campaign trail. Weekly snapshots of Web coverage reveal regional differences and contrast the perceptions of different stakeholders.
The system gathers content from environmental organizations, blogs, the Fortune 1000, and international media from the US, Canada, United Kingdom, Australia and New Zealand. Processing these sites yields more than 800,000 documents each week. An automated process identifies attention by counting references to a candidate. It measures sentiment towards the candidate by looking for positive and negative expressions that co-occur with these references. Keyword lists reflect the most important topics associated with the candidate. Interactive visualizations allow a closer examination of the gathered data. Information landscapes, geographic maps, ontology graphs and tag clouds help understand complex semantic relationships. Besides tracking recent developments, users can also cast their vote for their preferred candidate.