Evaluating and Validating Emotion Elicitation Using English and Arabic Movie Clips on a Saudi Sample

Sharifa Alghowinem, Roland Goecke, Michael Wagner, Areej Alwabil

Research output: Contribution to journalArticle

1 Citation (Scopus)
6 Downloads (Pure)

Abstract

With the advancement of technology in both hardware and software, estimating human affective states has become possible. Currently, movie clips are used as they are a widely-accepted method of eliciting emotions in a replicable way. However, cultural differences might influence the effectiveness of some video clips to elicit the target emotions. In this paper, we describe several sensors and techniques to measure, validate and investigate the relationship between cultural acceptance and eliciting universal expressions of affect using movie clips. For emotion elicitation, a standardised list of English language clips, as well as an initial set of Arabic video clips are used for comparison. For validation, bio-signal devices to measure physiological and behavioural responses associated with emotional stimuli are used. Physiological and behavioural responses are measured from 29 subjects of Arabic background while watching the selected clips. For the six emotions’ classification, a multiclass SVM (six-class) classifier using the physiological and behavioural measures as input results in a higher recognition rate for elicited emotions from Arabic video clips (avg. 60%) compared to the English video clips (avg. 52%). These results might reflect that using video clips from the subjects’ culture is more likely to elicit the target emotions. Besides measuring the physiological and behavioural responses, an online survey was carried out to evaluate the effectiveness of the selected video clips in eliciting the target emotions. The online survey, having on average 220 respondents for each clip, supported the findings.
Original languageEnglish
Article number2218
Pages (from-to)1-31
Number of pages31
JournalSensors
Volume19
Issue number10
DOIs
Publication statusPublished - 14 May 2019

    Fingerprint

Cite this