The emotion tracking tool working on the PDF EU site runs every five minutes and analyses the last 100 tweets with the hashtag #pdfeu.
The words contained within these tweets are then compared to data from the University of Florida (The Affective Norms for English Words). Within that data set each word covered (there are around a thousand in the set) is given a score for Valence (sad to happy on a scale 0-10), Arousal (asleep to awake on a scale of 0-10) and Dominance (feeling lack of control to feeling in control on a scale of 0-10). The scores are then collated and a mean percentage calculated. The overall emotional wellbeing score here is calculated as a mean of these.
It’s based on the sentiment analysis of Birmingham (UK) that’s been done by Jon Bounds.