Harvesting human feelings from blogs

We Feel Fine uses large scale blog analysis to provide a glimpse inside the hearts and minds of people all around the world. Once a sentence containing ‘I feel’ or ‘I am feeling’ is found, the system looks backward to the beginning of the sentence, and forward to the end of the sentence, and then saves the full sentence in a database. Once saved, the sentence is scanned to see if it includes one of about 5,000 pre-identified ‘feelings’. We Feel Fine is divided into six movements: Madness, Murmurs, Montage, Mobs, Metrics and Mounds.

These movements are represented in the We Feel Fine applet.

"The main insight we have gained is how amazingly personal people’s blogs can be", explained Jonathan Harris and Sepandar Kamvar, the authors, on an recent interview.

"The sentences in We Feel Fine are often sad and poignant (‘I feel so much of my dad alive inside of me that there isn’t even room for me’), and often quite banal (‘I feel comfortable that I don’t have a bra’). But above all, they are very human. The most common feeling by far is ‘better’. We can’t say for certain why this is the case, but we imagine that people return to their blogs after a bout of sadness or depression to announce their reclaimed happiness and begin to communicate again."

"We realised that many people were choosing blogs as a primary means of self-expression. Consequently, the internet, generally considered to be a cold, inhuman, emotionless space, was now harbouring a large amount of human emotion. We sought a way to illustrate this."

Probably the best way to illustrate the web as a truly human network.