See Buzz in action:

VIEW a video demonstration of Buzz.

VIEW a video demonstration of Buzz, exposing the buzz around Chicago Landmarks.

VIEW a video demonstration of Buzz, exposing the buzz around Wrigley Products.
The internet is a living, breathing reflection of who we are, what we think, and how we feel. The pages that make up the Web form the book of our contemporary life and culture. They are the ongoing and changing buzz of our world. The latest embodiment of this buzz is found in Web Logs (blogs). Not only are blogs widespread, but they are incredibly dynamic, with hundreds updated every minute. The existence of millions of blogs on the web has resulted in more than the mere presence of millions of online journals, but rather, they generate a collective buzz around the events in the world.

Buzz is a multimedia installation that exposes the buzz generated by blogs. Buzz finds the blogs which are compelling; those where someone is laying their feelings on the table, exposing a dream or a nightmare that they had, making a confession or apology to a close friend, or regretting an argument that they had with their mother or spouse. It embodies the blogger with virtual actors who externalize these monologues by reading them aloud. The focal point of the installation displays the most emotional and evocative words from the monologue, shown as falling text.

To find compelling stories, Buzz mines the blogophere, collecting blogs where the author describes an emotionally compelling situation: a dream, a nightmare, a fight, an apology, a confession, etc. After retrieving these blogs, Buzz performs affective classification to focus on blogs with a heightened emotional state. Other techniques, including syntax filtering and colloquial filtering, are used to ensure retrieval of appropriate content for the performance. After passing through these filters, the resulting story selections are compelling and emotional.

Several techniques are used to give Buzz a realistic feel. The actors are attentive to one another, turning to face the actor currently speaking. Gender classification is used to ensure that gender-specific stories are performed by virtual actors of the appropriate gender. A model of emotional speech emphasis is employed to enhance the cadence and prosody of text-to-speech technology.