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.
2025
19 citations
Innovative Approaches in Sensory Food Science: From Digital Tools to Virtual Reality
F. Cosme, T. Rocha, C. Marques, J. Barroso, A. Vilela
The food industry faces growing challenges due to evolving consumer demands, requiring digital technologies to enhance sensory analysis. Innovations such as eye-tracking, FaceReader, virtual reality (VR), augmented reality (AR), and artificial intelligence (AI) are transforming consumer behavior research by providing deeper insights into experiences. For instance, FaceReader captures emotional responses by analyzing facial expressions, offering valuable data on preferences for taste, texture, and aroma. Together, these provide a comprehensive understanding of the experience, aiding product development and branding. Electronic nose, tongue, and eye also replicate human capabilities, enabling objective and efficient assessment of aroma, taste, and color, supporting quality control processes. These advancements offer rapid, non-invasive, and reproducible assessments, benefiting industrial applications. By improving precision and efficiency in analysis, these tools help drive consumer satisfaction and competitiveness in the food industry. This review explores the latest methods shaping innovation.
2025
3 citations
An Artificial Intelligence Model for Sensing Affective Valence and Arousal from Facial Images
H. Nomiya, K. Shimokawa, S. Namba, M. Osumi, W. Sato
Artificial intelligence (AI) models can sense subjective affective states from facial images. Although recent psychological studies have indicated that dimensional aspects of valence and arousal are systematically associated with facial expressions, no AI model has been developed to estimate these from facial images based on empirical data. We developed a recurrent neural network-based model trained on our database containing participant valence/arousal ratings from video clips. Leave-one-out cross-validation supported the validity of the model for predicting subjective states. We further validated the effectiveness of the model by analyzing a dataset of facial expressions and arousal ratings from videos. The predicted second-by-second states, with a prediction performance comparable to FaceReader, a commercial facial expression analysis software, were used to estimate different affective states using a different approach. We constructed a graphical user interface to show real-time video and predicted affective states, and the model is the first distributable affective sensing model for facial images/videos. We anticipate it will be an AI model for sensing affective valence and arousal from facial images and have many practical uses, such as in mental health monitoring and marketing research.
2025
3 citations
Moderation Effect of Emotional Expressivity on the Associations Between Schizotypal Traits, Autistic Traits and Social Pleasure
L. Zhang, M. Wang, X. Fu, S. Chen, J. Gu, S. Li, M. Chu, Y. Wang, Y. Wang, R. C. K. Chan
Diminished social pleasure has been reported in people with schizophrenia and autism spectrum disorder (ASD). Previous studies suggested that emotional expressivity is closely correlated with social pleasure. However, the underlying psychological mechanisms between traits related to ASD, expressivity, and social pleasure remain unclear. This study aimed to investigate the relationship between subclinical schizotypal, autistic traits, facial expressions, and social pleasure. Eighty-six healthy participants (mean age = 20.35 ± 0.26 years, 44 males) were recruited to complete an emotion elicitation task by recalling memories, while their expressions were videotaped for computerized analysis using FaceReader. The intensity of different emotions (happy, sad, angry, surprised, scared, disgusted), valence, and arousal were extracted. Self-report Multidimensional Schizotypy Scale (MSS), Autism-Spectrum Quotient (AQ), and Anticipatory-Consummatory Interpersonal Pleasure (ACIPS) were administered to measure traits. Partial correlation and moderation analysis were performed. Both schizotypal and autistic traits were negatively correlated with social pleasure. Emotional expressivity had a significant moderating effect on the associations between schizotypal traits and social pleasure, and between autistic traits and social pleasure. Specifically, angry expression moderated the positive association between schizotypy and pleasure, and negative associations between autistic traits and pleasure. In addition, scared and surprised expressions moderated the associations between schizotypy and pleasure. Our findings identified the moderating role of emotional expressivity on the links between schizotypal and autistic traits and social pleasure, thereby revealing possible psychological mechanisms shared by both schizotypal and autistic traits, and highlighting potential targets for interventions in related psychopathological populations.
2025
61 citations
Inflence of Audiovisual Stimuli on Emotions and Sustainable Consumptions Behavior
M. A. Mateus, A. G. Rincon
In this research, FaceReader software is used to explore inflence of audiovisual stimuli on emotions and sustainable consumptions behavior, providing objective data on emotional responses and facial muscle activities.
2025
2 citations
Changes in facial expressions can distinguish Parkinson’s disease via Bayesian inference
M. Mouse, H. Gong, Y. Liu, F. Xu, X. Zou, M. Huang, X. Yang
Leveraging FaceReader technology, except for sad, scared, and disgusted, negative facial expressions were positively associated with the probability of PD. In addition, scared expressions generated by reading monosyllabic disyllables had the greatest effect on PD, while other multisyllabic expressions produced the least effect.
2024
8 citations
Comparative analysis of artificial intelligence and expert assessments in detecting neonatal procedural pain
V. Giordano, A. Luister, E. Vettorazzi, K. Wonka, N. Pointner, P. Steinbauer, M. Wagner, A. Berger, D. Singer, P. Deindl
This research evaluates the effectiveness of FaceReader and artificial intelligence in identifying procedural pain in newborns, comparing automated assessments with expert observations.