Emotion based systems have a typical process of recognition
of human emotion and generation of machine emotion. The
process has several stages for the recognition - classification,
quantification and mapping stages. Through this, a machine
can recognize a user’s emotion, and optionally, the machine
can generates its own emotional state or make recommendations
for users. Fig.1 shows an overall process that consists
of monitoring, recognition and emotional preference learning
module. The monitoring module collects device’s sensory data
such as touch and accelerometer with its occurrence time.
The emotion recognition module processes the collected data
to infer the human’s emotional state. When necessary, the
emotion recognition module can have additional attributes
such as memory, interaction and moods to enhance its accuracy
and performance. As in the bottom part of Fig.1, the emotional
preference learning module is responsible for building an
emotional preference matrix for the smartphone applications
(and or their embedding objects) by learning the difference
of quantificated emotional state between prior and posterior
behaviours(Eq.1). We will discuss details in the following
paragraphs.