Facial Expression Editing with Continuous Emotion Labels

AbstractDeficits in facial affect recognition have been repeatedly reported in schizophrenia patients. The hypothesis that this deficit is caused by poorly differentiated cognitive representation of facial expressions was tested in this study. To this end, performance of patients with schizophrenia and controls was compared in a new emotion-rating task. This novel approach allowed the participants to rate each facial expression at different times in terms of different emotion labels. Results revealed that patients tended to give higher ratings to emotion labels that did not correspond to the portrayed emotion, especially in the case of negative facial expressions (p < .001, η2 = .131). Although patients and controls gave similar ratings when the emotion label matched with the facial expression, patients gave higher ratings on trials with "incorrect" emotion labels (ps < .05). Comparison of patients and controls in a summary index of expressive ambiguity showed that patients perceived angry, fearful and happy faces as more emotionally ambiguous than did the controls (p < .001, η2 = .135). These results are consistent with the idea that the cognitive representation of emotional expressions in schizophrenia is characterized by less clear boundaries and a less close correspondence between facial configurations and emotional states.

Download Full-text

Automatic Human Emotion Classification in Web Document Using Fuzzy Inference System (FIS)

International Journal of Technology and Human Interaction ◽

10.4018/ijthi.2020010107 ◽

2020 ◽

Vol 16 (1) ◽

pp. 94-104 ◽

Cited By ~ 14

Author(s):

P Mohamed Shakeel ◽

S Baskar

Keyword(s):

Facial Expression ◽

Web 2.0 ◽

Information Extraction ◽

Rapid Growth ◽

Extraction Methods ◽

Textual Information ◽

Fast Development ◽

Machine Interface ◽

Document Categorization ◽

Emotion Labels

Textual information mining deals with various information extraction methods that can be evolved from the rapid growth of textual information through human machine interface for analyzing emotions which are taken by a facial expression. The problem of emotions in text is concerned with the fast development of web 2.0 documents that are assigned by users with emotion labels, namely: sadness, surprise, happiness, empathy, anger, warmness, boredom, and amusement. Such emotions can give a new characteristic for document categorization. Textual information mining deals with various information extraction methods that can evolved from the rapid growth of textual information through a human machine interface for analyzing emotions, which are taken by a facial expression. The problem of emotions from text is concerned with the fast development of web 2.0 documents that are assigned by users with emotion labels. Such emotions can give a new characteristic for document categorization.

Download Full-text