Developing HEO Human Emotions Ontology

A big issue in the task of annotating multimedia data about dialogs and associated gesture and emotional state is due to the great variety of intrinsically heterogeneous metadata and to the impossibility of a standardization of the used descriptor in particular for the emotional state of the subject. We propose to tackle this problem using the instruments and the vision offered by Semantic Web through the development of an ontology for human emotions that could be used in the annotation of emotion in multimedia data, supplying a structure that could grant at the same time flexibility and interoperability, allowing an effective sharing of the encoded annotations between different users.