For my first option, I will use Twitter’s search API to find tweets by all users in a certain area, using the GPS tag information posted with the tweets, then using a computer program I will calculate the mood of that persons tweet by searching the tweet for keywords which are in a database assigning a number between -10 and +10 to attribute mood to that word. The system will then average out the moods on each tweet and assign a number using mood colours, on a simple level it would be Sad to Happy but could use other ranges too…

Sad                                                                                                  Happy

-10 -9 -8 -7 -6 -5 -4 -3 -2 -1 0 +1 +2 +3 +4 +5 +6 +7 +8 +9 +10

Red                                        White                                               Green

So for the sentence, I hate him, he has ruined my life it might detect hate as a -10 and ruined as -3, -3 + -10 = -13 / 2 = -6.5 which may be a orange/red colour.

The users would interact with this by controling the search location on a Google map and using physical sliders to define a search range which is netrual giving a full range of emotions of biased towards an emotion such as anger.

The results would be shown in a grid of colour changing orbs which reprisent a live feed of the twitters.