Development and Validation of the AIIMS Facial Toolbox for Emotion Recognition

Abstract

Background: Emotional facial expression database, used in emotion regulation studies, is a special set of pictures with high social and biological relevance. We present the AIIMS Facial Toolbox for Emotion Recognition (AFTER) database. It consists of pictures of 15 adult professional artists displaying seven facial expressions—neutral, happiness, anger, sadness, disgust, fear, and surprise. Methods: This cross-sectional study enrolled 15 volunteer students from a professional drama college in India (six males and nine females; mean age = 26.2 ± 1.93 years). They were instructed to pose with different emotional expressions in high and low intensity. A total of 240 pictures were captured in a brightly lit room against a common, light background. Each picture was validated independently by 19 mental health professionals and two professional teachers of dramatic art. Apart from recognition of emotional quality, ratings were done for each emotion on a 5-point Likert scale with respect to three dimensions—intensity, clarity, and genuineness. Results are discussed in terms of mean scores on all four parameters. Results: The percentage hit rate for all the emotions, after exclusion of contempt, was 84.3%, with the mean kappa for emotional expression being 0.68. Mean scores on intensity, clarity, and genuineness of the emotions depicted in the pictures were high. Conclusions: The database would be useful in the Indian context for researching facial emotion recognition. It has been validated among a group of experts and was found to have high inter-rater reliability.

Development and Validation of the Emotion Laden Sentences Toolbox for Emotion Recognition (ELSTER)

“… 34 However, just like Ekman, this category along with ‘others’, was eliminated due to low accuracy rates in phase I. Similarly, our findings from the previous study on emotion recognition of facial emotion in All India Institute of Medical Sciences (AIIMS) Facial Toolbox for Emotion Recognition (AFTER) database, 18 also found that the contempt emotion had poor hit rates among the study population. The same was also true for the Dynamic Emotion Laden Inventory of Videos for Emotion Recognition (DELIVER) database that assessed emotion recognition through videos of emotion expressions.…”

“…The data presented in the current article on the development of Emotion Laden Sentences Toolbox for Emotion Recognition (ELSTER) database is part of a larger study comprising the development of a larger toolbox for varying facets of emotion recognition. 18 , 32 This cross-sectional study was conducted from March 2019 to August 2021 at the Department of Psychiatry, All India Institute of Medical Sciences, New Delhi, India. The Institute Ethics Committee approved the study.…”

“…Based on the previous literature, eight emotion expressions were selected—neutral, happiness, anger, sadness, disgust, contempt, fear, and surprise. 18 …”

“…Based on the previous literature, eight emotion expressions were selected-neutral, happiness, anger, sadness, disgust, contempt, fear, and surprise. 18 The emotion-laden sentences were initially selected in English language from freely available online books, novels, and other textual literature. Ten sentences depicting each emotional state were selected keeping the length to a maximum of 40 words in proper grammatical format by three researchers.…”

“…16,17 There are several tasks that are frequently used for assessing emotion recognition, each of which concentrates on a distinct type of emotional signal. While most of these measures are based on recognizing emotions in non-verbal stimuli, particularly facial expressions, 18 there are a few databases that evaluate other forms of non-verbal expressions. The Reading the Mind in the Eyes Test (RMET), evaluates the capacity to attribute emotions by looking at photos of people's eyes.…”