The final goal of Affective Computing is in allowing to recognize human emotional states by means of automatic procedures. Despite scientific literature evidences the concrete usefulness of possible approaches based on biosignals analysis to detect and correctly classify emotions, existing systems and tools are generally too invasive for common subjects and in addition they are too intensive in terms of needed processing. Hence, practical application and effectiveness of such kind of solutions is really limited to laboratory-controlled contexts and this seriously compromises their porting to real scenarios. This paper aims to propose an innovative approach for the automatic interpretation of affective information. Biosignal features of subjects stimulated by emotions are extracted and annotated automatically adopting a semantically rich and non-ambiguous language. Logic-based matchmaking, leveraging non-standard inference algorithms, allows to detect the most probable emotional state of the subject. The proposed approach has been validated through the implementation and the experimental evaluation of a prototypical system.

From biosignals to affective states: A semantic approach

Scioscia, Floriano;Ruta, Michele;Di Sciascio, Eugenio
2018-01-01

Abstract

The final goal of Affective Computing is in allowing to recognize human emotional states by means of automatic procedures. Despite scientific literature evidences the concrete usefulness of possible approaches based on biosignals analysis to detect and correctly classify emotions, existing systems and tools are generally too invasive for common subjects and in addition they are too intensive in terms of needed processing. Hence, practical application and effectiveness of such kind of solutions is really limited to laboratory-controlled contexts and this seriously compromises their porting to real scenarios. This paper aims to propose an innovative approach for the automatic interpretation of affective information. Biosignal features of subjects stimulated by emotions are extracted and annotated automatically adopting a semantically rich and non-ambiguous language. Logic-based matchmaking, leveraging non-standard inference algorithms, allows to detect the most probable emotional state of the subject. The proposed approach has been validated through the implementation and the experimental evaluation of a prototypical system.
2018
2nd International Conference on Computational Biology and Bioinformatics, ICCBB 2018
978-1-4503-6552-9
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/176965
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact