Emotion, Content, and Context in Sound and Music - Game Sound Technology and Player Interaction: Concepts and Developments - page 255

Figure 8. Emotion, Content and Context Aware Playlist System

Given currently available technology, it is also
relatively easy to find equipment that allows the
measurement of a user's movement. This was re-
alised in our case by employing the wireless hand
controller from the Nintendo Wii: the Wiimote.
The Wiimote, when compared to other alterna-
tives, is a cheap device that allows measurement
of three-dimensions of movement. The Wiimote
is almost universally accessible since it employs
the Bluetooth communication protocol to send
and receive data to a paired host. As Maurizio
and Samuele (2007) demonstrate, valuable mo-
tion information can be retrieved through the
accelerometers contained in the Wii controller.

information acquired from the user to arrive at an
estimate of the user's emotional state ( E -state). To
achieve this, we developed a small scale system
that would work from a number of simulated fac-
tors (controlled by the researcher) and also live
data extracted from sensors, principally the Wii
controller. This system was designed to work with
a small music database consisting of eight songs,
shown in Table 4, and rank these songs in order of
most suitable, based upon the estimated E-state.
To begin working with the motion data from
the Wiimote controller, we attempted to work with
four simple locomotive states: standing, walking,
jogging, and running. These simple locomotive
states were believed to be detectable from not only
the Wiimote but a range of motion measurement
devices such as the accelerometers built into the
Apple iPhone/iPod, as well as higher-level systems
such as a Qualisys motion capture system (which
we also had access to and allows us to verify the

Implementation and Initial Results

Our initial work in this field sought to demon-
strate the ability to attain, analyse and correlate
content-related data about music and contextual