| abstract
| - People’s emotions are not always detectable, e.g. if a person has difficulties/lack of skills in expressing emotions, or if people are geographically separated/communicating online). Brain-computer interfaces (BCI) could enhance non-verbal communication of emotion, particularly in detecting and responding to users’ emotions e.g. music therapy, interactive software. Our pilot study Music Emotion Capture 1 detects, models and sonifies people’s emotions based on their real-time emotional state, measured by mapping EEG feedback onto a valence-arousal emotional model 2 based on [3]. Though many practical applications emerge, the work raises several ethical questions, which need careful consideration. This poster discusses these ethical issues. Are the work’s benefits (e.g. improved user experiences; music therapy; increased emotion communication abilities; enjoyable applications) important enough to justify navigating the ethical issues that arise? (e.g. privacy issues; control of representation of/reaction to users’ emotional state; consequences of detection errors; the loop of using emotion to generate music and music affecting the emotion, with the human in the process as an “intruder”).
1 Langroudi, G., Jordanous, A., & Li, L. (2018). Music Emotion Capture: emotion-based generation of music using EEG. Emotion Modelling and Detection in Social Media and Online Interaction symposium @ AISB 2018, Liverpool. 2 Paltoglou, G., & Thelwall, M. (2012). Seeing stars of valence and arousal in blog posts. IEEE Transactions on Affective Computing, 4(1) [3] Russell, J.A. (1980). ‘A circumplex model of affect’, Journal of Personality and Social Psychology, 39
- People’s emotions are not always detectable, e.g. if a person has difficulties/lack of skills in expressing emotions, or if people are geographically separated/communicating online). Brain-computer interfaces (BCI) could enhance non-verbal communication of emotion, particularly in detecting and responding to users’ emotions e.g. music therapy, interactive software. Our pilot study Music Emotion Capture 1 detects, models and sonifies people’s emotions based on their real-time emotional state, measured by mapping EEG feedback onto a valence-arousal emotional model 2 based on [3]. Though many practical applications emerge, the work raises several ethical questions, which need careful consideration. This poster discusses these ethical issues. Are the work’s benefits (e.g. improved user experiences; music therapy; increased emotion communication abilities; enjoyable applications) important enough to justify navigating the ethical issues that arise? (e.g. privacy issues; control of representation of/reaction to users’ emotional state; consequences of detection errors; the loop of using emotion to generate music and music affecting the emotion, with the human in the process as an “intruder”).
1 Langroudi, G., Jordanous, A., & Li, L. (2018). Music Emotion Capture: emotion-based generation of music using EEG. Emotion Modelling and Detection in Social Media and Online Interaction symposium @ AISB 2018, Liverpool. 2 Paltoglou, G., & Thelwall, M. (2012). Seeing stars of valence and arousal in blog posts. IEEE Transactions on Affective Computing, 4(1) [3] Russell, J.A. (1980). ‘A circumplex model of affect’, Journal of Personality and Social Psychology, 39
|
![[RDF Data]](/fct/images/sw-rdf-blue.png)
![[cxml]](/fct/images/cxml_doc.png)
![[csv]](/fct/images/csv_doc.png)
![[text]](/fct/images/ntriples_doc.png)
![[turtle]](/fct/images/n3turtle_doc.png)
![[ld+json]](/fct/images/jsonld_doc.png)
![[rdf+json]](/fct/images/json_doc.png)
![[rdf+xml]](/fct/images/xml_doc.png)
![[atom+xml]](/fct/images/atom_doc.png)
![[html]](/fct/images/html_doc.png)