Scientific publications
Read about the research that supports the FaceReader Ecosystem
Over the past 20+ years, our facial coding platform and its embedded technologies have been the subject as well as the preferred instrument for numerous accredited scientific studies. Below we present a comprehensive overview of the literature that has emerged from these studies, highlighting and validating the cutting-edge technology of FaceReader Online.
2023
8 citations
The cross-race effect in automatic facial expression recognition violates measurement invariance
Y. T. Li, S. Yeh, T. R. Huang
Emotion has been a subject undergoing intensive research in psychology and cognitive neuroscience over several decades. Recently, more studies of emotion have adopted automatic rather than manual methods for facial expression recognition to analyze images or videos of human faces. Compared to manual methods, these computer-vision-based methods can help objectively and rapidly analyze a large amount of data. These methods are also validated and believed to be accurate in their judgments. However, they often rely on statistical learning models (e.g., deep neural networks), which are intrinsically inductive and thus suffer from problems of induction. Specifically, that were trained primarily on Western faces may not generalize well and accurately to judge Eastern faces, then jeopardize measurement invariance of emotions in cross-cultural studies. To demonstrate such possibility, this study carries out cross-racial validation of two popular systems—FaceReader and DeepFace—using face datasets. Although both systems could achieve overall high accuracies in judgments by category on datasets, they performed relatively poorly, especially for negative emotions. While the results caution use of non-Western, they suggest measurements of happiness outputted by invariant across races, hence still utilized for positive psychology.
2023
6 citations
Predicting Perceived Hedonic Ratings through Facial Expressions of Different Drinks
Y. Matsufuji, K. Ueji, T. Yamamoto
Previous studies have established the utility of facial expressions as an objective assessment approach for determining hedonics (overall pleasure) in food and beverages. This study endeavors to validate the conclusions drawn from preceding research, illustrating that facial expressions prompted by tastants possess the capacity to forecast perceived hedonic ratings of these tastants. Facial expressions of 29 female participants, aged 18-55 years, were captured using a digital camera during their consumption of diverse concentrations of solutions representative of five basic tastes. Employing the widely employed expression analysis application FaceReader, emotions were meticulously assessed, identifying seven emotions (surprise, happiness, scare, neutral, disgust, sadness, anger) characterized by scores ranging from 0-1, a numerical manifestation of emotional intensity. Simultaneously, participants rated each solution, utilizing a scale spanning -5 (extremely unpleasant) to +5 (pleasant). A multiple linear regression analysis model was devised. The model’s efficacy was scrutinized assessing emotion when applied to 11 additional taste solutions, sampled from 20 other participants. The anticipated results demonstrated robust alignment and agreement with observed ratings, underpinning the validity of earlier findings, even when incorporating software-based stimuli across a varied participant base. We discuss some limitations and practical implications of our technique in predicting beverage hedonics.
2023
3 citations
Exploring effects of response biases in affect induction procedures
D. Moulds, J. Meyer, J. F. McLean, V. Kempe
This study examined whether self-reports or ratings of experienced affect, often used as manipulation checks on the efficacy of affect induction procedures (AIPs), reflect genuine changes in affective states, rather than response biases arising from demand characteristics or social desirability effects. In a between-participants design, participants were exposed to positive, negative, and neutral images with valence-congruent music sound to induce happy, sad mood. Half had actively appraise each image whereas the other half viewed passively. We hypothesised that if valence are subject then they should target mood same way for active appraisal and passive exposure. Participants encountered stimuli in both conditions. We also tested whether AIPs resulted in mood-congruent facial expressions analysed by FaceReader (see behavioural indicators to corroborate self-reports). The results showed while participants’ reflected induced valence, difference between positive was significantly attenuated in condition, suggesting after not entirely reflection biases. However, there were no effects on scores, line theories questioning existence cross-culturally inter-individually universal states. Efficacy AIPs is therefore best checked using behavioural indicators.
2023
11 citations
Quantifying the efficacy of an automated facial coding software using videos of parents
R. C. Burgess, I. Culpin, I. Costantini, H. Bould, I. Nabney, R. M. Pearson
Leveraging FaceReader technology, we discuss the implications of our findings in the context of future automated facial coding studies, and we emphasise the need to consider gender-specific influences in research.
2023
24 citations
Differential responses in the mirror neuron system during imitation of individual emotional facial expressions and association with autistic traits
W. Zhao, Q. Liu, X. Zhang, X. Song, Z. Zhang
In this research, FaceReader software is used to explore differential responses in the mirror neuron system during imitation of individual emotional facial expressions and association with autistic traits, providing objective data on emotional responses and facial muscle activities.
2023
102 citations
Risk, Trust, and Emotion in Online Pharmacy Medication Purchases: Multimethod Approach Incorporating Customer Self-Reports, Facial Expressions, and Neural Activation (Preprint)
S. Ersöz, A. Nissen, R. Schütte
BACKGROUND: Online pharmacies are used less than other e-commerce sites in Germany. Shopping behavior does not correspond to consumption behavior, as online purchases predominantly made for over-the-counter (OTC) medications. OBJECTIVE: The objective of this study was to understand the purchasing experiences of pharmacy customers in terms of critical factors for adoption. METHODS: This examined perceived risk, trust, and emotions related to medications and, consequently, purchase intention toward pharmacies. In a within-subjects design (N=37 participants), 2 German with different perceptions of risk, trust, were investigated their main business, namely OTC and prescription drugs. results preliminary led 1 high significantly low self-reported by prestudy sample. Emotions measured multimethod approach during and after situation follows: (1) neural evaluation processes using functional near-infrared spectroscopy, (2) automated direct motor response use via facial expression analysis (FaceReader), and (3) subjective evaluations through self-reports. Following shopping at both product types, assessed self-assessments. RESULTS: rated differently emotions, intention. high-risk also having lower vice versa. Significantly stronger negative emotional expressions on customers’ faces activations ventromedial prefrontal cortex, dorsomedial when drugs from low-risk pharmacy, combined line this, self-ratings indicated higher pharmacy. Moreover, ratings showed CONCLUSIONS: Using measurements, we that preceding activation subsequent verbal reflected immediate expressions. High-risk lead trigger imply loss. Low-risk weaker signify certainty reward. may provide an explanation why purchased more frequently CLINICALTRIAL: University Duisburg-Essen, Germany (21-9995-BO)