EEG-based detection of emotional valence towards a reproducible measurement of emotions

Abstract

A methodological contribution to a reproducible Measurement of Emotions for an EEG-based system is proposed. Emotional Valence detection is the suggested use case. Valence detection occurs along the interval scale theorized by the Circumplex Model of emotions. The binary choice, positive valence vs negative valence, represents a first step towards the adoption of a metric scale with a finer resolution. EEG signals were acquired through a 8-channel dry electrode cap. An implicit-more controlled EEG paradigm was employed to elicit emotional valence through the passive view of standardized visual stimuli (i.e., Oasis dataset) in 25 volunteers without depressive disorders. Results from the Self Assessment Manikin questionnaire confirmed the compatibility of the experimental sample with that of Oasis. Two different strategies for feature extraction were compared: (i) based on a-priory knowledge (i.e., Hemispheric Asymmetry Theories), and (ii) automated (i.e., a pipeline of a custom 12-band Filter Bank and Common Spatial Pattern). An average within-subject accuracy of 96.1 %, was obtained by a shallow Artificial Neural Network, while k-Nearest Neighbors allowed to obtain a cross-subject accuracy equal to 80.2%.

WITHDRAWN: Emotional Brain activity Evaluation in Diabetes mellitus type 2: A case report

“…Valence, a measure of an emotion's positive or negative intensity, is used in the Circumplex Model 2 of emotion. The Discrete Model of Emotions offers a different method for studying emotions (Apicella et al, 2021), by using categorized approach for distinct basic emotions which are characterized by consistent patterns of triggers, expressed behavior, and related subjective experiences. (Eva Hudlicka, 2017).…”

A Survey on EEG-Based Solutions for Emotion Recognition With a Low Number of Channels

“…The commercial devices provided with a number of chan- . The OpenBCI, the Mindlink, the Emotiv Insight, the Nexus10, the Nexus4, and the abmedica Helmate are employed in the minority of cases [82], [121]- [127]. Also in this case it is possible to distinguish between compliant and non-compliant devices.…”

A Review of AI Cloud and Edge Sensors, Methods, and Applications for the Recognition of Emotional, Affective and Physiological States

“…Gannouni et al [ 283 ] argue that emotion recognition using EEG signals needs a multi-disciplinary approach, encompassing areas such as psychology, engineering, neuroscience, and computer science. With the aim of improving the reproducibility of emotion measurement based on EEG, Apicella et al [ 35 ] have proposed an emotional valence detection method for a system based on EEG, and their experiments proved an accuracy of 80.2% in cross-subject analysis and 96.1% in within-subject analysis. Dixson et al [ 284 ] have pointed out that facial hair may interfere with detection of emotional expressions in a visual search.…”

“…Many works have focused on emotion detection using different techniques [ 35 , 283 , 284 , 324 , 325 , 326 , 327 ]. Specific tasks (e.g., WASSA-2017, SemEval) have also included emotion detection tasks that cover four categories of emotions (anger, fear, sadness, and joy) [ 320 ].…”

“…Indeed, the biometrics and neuroscience field has been the focus of studies by many researchers who have achieved significant results. A number of neuroscience studies have analyzed the detection and recognition of human arousal [ 34 ], valence [ 35 , 36 ], affective attitudes [ 36 , 37 ], emotional [ 38 , 39 , 40 , 41 ], and physiological [ 42 ] states (AFFECT) by capturing human signals.…”