The use of social networks has grown exponentially in recent years. The large 
amount of data available in these networks can be effectively utilized in many machine 
learning applications. This paper proposes a framework of an emotion recognition system 
that fetches huge amount of face images from the social networks into a cloud. In the cloud, 
the problem of the unlabeled facial images is handled by applying an active learning 
approach. For the feature extraction, an interlaced derivative pattern is used, while for a ...