6533b855fe1ef96bd12b13ed
RESEARCH PRODUCT
Combining Supervised and Unsupervised Learning to Discover Emotional Classes
Pablo Arnau-gonzalezAladdin AyeshOlga C. SantosMiguel Arevalillo-herráezsubject
Computer science050109 social psychologyuser modelling02 engineering and technologyMachine learningcomputer.software_genrePersonalization0202 electrical engineering electronic engineering information engineering0501 psychology and cognitive sciencesEmotion recognitionEEGValence (psychology)Affective computingaffective computingclass discoverybusiness.industry05 social sciencesSupervised learningPattern recognitionHybrid approachComputingMethodologies_PATTERNRECOGNITIONUnsupervised learning020201 artificial intelligence & image processingArtificial intelligencebusinesscomputercluster analysisdescription
Most previous work in emotion recognition has fixed the available classes in advance, and attempted to classify samples into one of these classes using a supervised learning approach. In this paper, we present preliminary work on combining supervised and unsupervised learning to discover potential latent classes which were not initially considered. To illustrate the potential of this hybrid approach, we have used a Self-Organizing Map (SOM) to organize a large number of Electroencephalogram (EEG) signals from subjects watching videos, according to their internal structure. Results suggest that a more useful labelling scheme could be produced by analysing the resulting topology in relation to user reported valence levels (i.e., pleasantness) for each signal, refining the original set of target classes.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2017-04-02 |