Comparing the Affectiva iMotions Facial Expression Analysis Software with EMG

Abstract: People’s faces display emotions, informing others about their affective states. In order to measure facial displays of emotion, Electromyography (EMG) has widely been used, requiring electrodes and technical equipment. More recently, emotion recognition software has been developed that detects emotions from videos. However, its validity and comparability to EMG is unclear. The aim of the current study was to validate the Affectiva Affdex emotion recognition software by iMotions for happy, angry and neutral faces and to compare it to EMG. Twenty participants displayed these facial expressions while videos or EMG were recorded. Findings show that happy and angry expressions can reliably be detected by the software and by EMG, while neutral faces are more often falsely identified as negative by EMG than by the software. EMG and software values correlate highly. In conclusion, Affectiva Affdex software can reliably identify emotions and its results are comparable to EMG findings.