Dataset Information

Emotion recognition bias depends on stimulus morphing strategy.

ABSTRACT: Emotion recognition is vital for social interactions, and atypical (or biased) emotion recognition has been linked to mental health disorders including depression and anxiety. However, biases in emotion recognition vary across studies, and it is unclear whether this reflects genuine group differences in psychological processes underlying emotion recognition or differences in methodologies. One common method to measure biases in emotion recognition involves morphing a face between two emotional expressions in different ratios and asking participants to categorise the faces as belonging to one of the two emotion categories ('direct-morphing' method). However, this method creates morphed faces that are not ecologically valid. Alternatively, faces may be morphed through a neutral expression ('morphing-through-neutral' method), which is more ecologically valid since emotional expressions usually start from a neutral face. To compare these two approaches, we measured emotion recognition biases using two morphing techniques in 136 participants who also completed measures of anxiety (GAD-7) and depression (PHQ-9). Biases obtained using the two methods differed significantly: In the direct-morphing method, participants perceived the central 50% happy/50% angry face as slightly happy, whereas in the morphing-through-neutral method the neutral face was seen as angry. There were no associations between biases and depression or anxiety scores for either morphing method. This study is the first to directly compare emotion recognition biases obtained using two different morphing methods and is a first step towards reconciling discrepancies in the literature.

SUBMITTER: Vikhanova A

PROVIDER: S-EPMC9255837 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Emotion recognition is key to interpersonal communication and to human-machine interaction. Body expression may contribute to emotion recognition, but most past studies focused on a few motions, limiting accurate recognition. Moreover, emotions in most previous research were acted out, resulting in non-natural motion, which is unapplicable in reality. We present an approach for emotion recognition based on body motion in naturalistic settings, examining authentic emotions, natural movement, and a broad collection of motion parameters. A lab experiment using 24 participants manipulated participants' emotions using pretested movies into five conditions: happiness, relaxation, fear, sadness, and emotionally-neutral. Emotion was manipulated within subjects, with fillers in between and a counterbalanced order. A motion capture system measured posture and motion during standing and walking; a force plate measured center of pressure location. Traditional statistics revealed nonsignificant effects of emotions on most motion parameters; only 7 of 229 parameters demonstrate significant effects. Most significant effects are in parameters representing postural control during standing, which is consistent with past studies. Yet, the few significant effects suggest that it is impossible to recognize emotions based on a single motion parameter. We therefore developed machine learning models to classify emotions using a collection of parameters, and examined six models: k-nearest neighbors, decision tree, logistic regression, and the support vector machine with radial base function and linear and polynomial functions. The decision tree using 25 parameters provided the highest average accuracy (45.8%), more than twice the random guess for five conditions, which advances past studies demonstrating comparable accuracies, due to our naturalistic setting. This research suggests that machine learning models are valuable for emotion recognition in reality and lays the foundation for further progress in emotion recognition models, informing the development of recognition devices (e.g., depth camera), to be used in home-setting human-machine interactions.

Dataset Information

Emotion recognition bias depends on stimulus morphing strategy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets