Publication Tag: Affective Computing

This research uses facial expression recognition software (FaceReader) to explore the influence of different sound interventions on the emotions of older people with dementia. The field experiment was carried out in a public activity space in an adult care facility. Three intervention sources were used, namely, music, stream, and birdsong. Data collected through the Self-Assessment Manikin Scale (SAM) were compared with (FER) data. FaceReader identified differences in emotional responses. Participants had significantly higher valence for all three interventions than without (p < 0.01). Indices of sadness, fear, disgust differed between interventions. For example, before the start of birdsong intervention, the index initially increased by 0.06 from 0 s to about 20 s, followed by a linear downward trend, an average reduction of 0.03 per s. In addition, arousal was lower when interventions began before, rather than concurrently with, the start of birdsong (p < 0.01). Moreover, stream interventions, there were significant days (p < 0.05 or p < 0.01). Furthermore, age and gender. Finally, comparison of SAM and FER results showed that music (first 80 s) helps predict dominance (r = 0.600), acoustic comfort (r = 0.545); birdsong (first 40 s) predicts pleasure (r = 0.770), acoustic comfort (r = 0.766); and music (r = 0.824), birdsong (r = 0.891).