Descripción
|
|
---|---|
This paper contributes to the field of affective video content analysis through the novel employment of electrodermal activity (EDA) measurements as ground truth for machine learning algorithms. The variation of the electrical properties of the skin, known as EDA,isapsychophysiologicalindicatorwidelyusedinmedicine, psychologyandneurosciencewhichcanbeconsideredasomatic markeroftheemotionalandattentionalreactionofsubjectstowards stimuli.Oneofitsmainadvantagesisthattherecordedinformation is not biased by the cognitive process of giving an opinion or a score to characterize the subjective perception. In this work, we predict the levels of emotion and attention, derived from EDA records, by means of a small set of low-level visual descriptors computedfromthevideostimuli.Linearregressionexperiments show that our descriptors predict significantly well the sum of emotionandattentionlevels,reachingacoefficientofdetermination R2 = 0.25.Thisresultsetsapromisingpathforfurtherresearchon thepredictionofemotionandattentionfromvideosusingEDA. | |
Internacional
|
Si |
Nombre congreso
|
WI '17 International Conference on Web Intelligence |
Tipo de participación
|
960 |
Lugar del congreso
|
Leipzig, Germany |
Revisores
|
Si |
ISBN o ISSN
|
978-1-4503-4951-2 |
DOI
|
10.1145/3106426.3109418 |
Fecha inicio congreso
|
23/08/2017 |
Fecha fin congreso
|
26/08/2017 |
Desde la página
|
914 |
Hasta la página
|
923 |
Título de las actas
|
Proceedings WI '17 International Conference on Web Intelligence |