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.
2017
21 citations
Asians’ Facial Responsiveness to Basic Tastes by Automated Facial Expression Analysis System
Zhi, Cao, Cao
Growing evidence indicates that consumer choices are predominantly driven by unconscious mechanisms, measurable through behavioral assessments. This study applies automatic facial expression analysis to represent consumers’ emotions and explores the relationship between sensory perception and facial responses. Participants were exposed to basic taste solutions—sourness, sweetness, bitterness, umami, and saltiness—at six concentration levels, plus water, encompassing most flavors found in food and beverages. The study focuses on analyzing facial expression characteristics and their correlation with hedonic liking among Asian consumers, addressing a gap in research that has primarily centered on Western populations. Results demonstrate that facial expressions can distinguish between stimuli of varying concentrations and hedonic levels. Perceived liking increased at lower concentrations and decreased at higher ones, with medium concentrations being most pleasant, except for sweetness and bitterness. High correlations were found between perceived intensities of bitterness, umami, saltiness, and facial reactions of disgust and fear. Disgust and anger expressions characterized “dislike,” happiness indicated “like,” and neutral expressions represented “neither like nor dislike.” These findings align with sensory emotions elicited by basic taste solutions and are consistent with research on Western consumers. The study underscores the potential of automatic facial expression analysis in understanding true consumer emotions, aiding product development and improvement.
2017
20 citations
Clusters of Nonverbal Behaviors Differ According to Type of Question and Veracity in Investigative Interviews in a Mock Crime Context
Matsumoto & Hwang
Evaluating truthfulness and detecting deception is a capstone skill of criminal justice professionals, and researchers have long examined nonverbal cues to aid in such determinations. This paper examines the notion that testing clusters of nonverbal behaviors is a more fruitful way of making such determinations than single, specific behaviors. Participants from four ethnic groups participated in a mock crime and either told the truth or lied in an investigative interview. Fourteen nonverbal behaviors of the interviewees were coded from the interviews; differences in the behaviors were tested according to type of question and veracity condition. Different types of questions produced different nonverbal reactions. Clusters of nonverbal behaviors differentiated truth tellers from liars, and the specific clusters were moderated by question. Accuracy rates ranged from 62.6 to 72.5% and were above deception detection accuracy rates for humans and random data. These findings have implications for practitioners as well as future research and theory.
2017
16 citations
Positive facial expressions during retrieval of self-defining memories
Gandolphe, Nandrino, Delelis, Ducro, Lavallee, Saloppe, Moustafa, El Haj
This study investigates facial expressions during the retrieval of self-defining memories—vivid and emotionally intense memories of enduring concerns or unresolved conflicts. Participants self-rated the emotional valence of their self-defining memories, while autobiographical retrieval was analyzed using facial analysis software . This software synthesizes facial expression information to categorize expressions as neutral, happy, sad, surprised, angry, scared, or disgusted. Findings revealed that participants exhibited more emotional than neutral facial expressions during the retrieval of self-defining memories, with a predominance of positive over negative expressions. Interestingly, participants attributed positive valence to the retrieved memories. These findings demonstrate a consistency between facial expressions and the subjective emotional experience of self-defining memories, providing valuable physiological insights into the emotional experience of the past.
2017
66 citations
The Effect of Parental Modeling on Child Pain Responses: The Role of Parent and Child Sex
Boerner, Christine, McGrath, LoLordo, Uher
Social modeling is a process by which pain behaviors are learned, and research has found parents act as models for their children’s behavior. Despite social learning theory predicting that same-sex models have greater effect, no experimental investigation to date has examined the role of sex of the model or observer in social learning of pediatric pain. The present study recruited 168 parent-child dyads in which children were generally healthy and 6 to 8 years old. Unbeknownst to their child, parents were randomly assigned to exaggerate their expression of pain, minimize their expression of pain, or act naturally during the cold pressor task . Parents completed the CPT while their child observed, then children completed the CPT themselves. Children whose parents were in the exaggerate condition reported higher anxiety than children of parents in the minimize condition. Additionally, girls in the exaggerate condition rated their overall pain intensity during the CPT significantly higher than boys in the same condition. No child sex differences were observed in pain intensity for the control or minimize conditions. Parent expressions of pain affects children’s anxiety, and sex-specific effects of parental exaggerated pain expression on children’s own subsequent pain experience are present.
Perspective: This article describes how parental expressions of pain influence children’s pain and anxiety, specifically examining the relevance of parent and child sex in this process. These findings have implications for children of parents with chronic pain, or situations in which parents experience pain in the presence of their child .
2017
27 citations
Sensory-specific satiety: Added insights from autonomic nervous system responses and facial expressions
He, Boesveldt, Delplanque, de Graaf, de Wijk
As a food is consumed, its perceived pleasantness declines compared to that of other foods. Although this phenomenon, referred to as sensory-specific satiety, is well-established by means of measuring food intake and pleasantness ratings, this study was aimed at gaining more insight into the mechanisms that underlie such cognitive output behavior using two measures used in emotion research, namely Autonomic Nervous System responses and facial expressions. Twenty-four healthy female participants visited four times in a hungry state, in which they received 4 different semi-liquid meals delivered via a time-controlled pump leading to sensory-specific satiety. Before and after the meals they were presented with a sip of all four different test meals where ANS responses and facial expressions were recorded. As expected, pleasantness ratings showed a significant decrease after eating the same meal or a meal similar in taste , and less decrease after eating a meal with a different taste. In general, consumption of the test meals resulted in increased heart rate, reduced skin conductance and skin temperature, as well as intensified anger and disgusted facial expressions . In addition, skin conductance, skin temperature, sad and angry expressions also showed effects reflecting sensory-specific satiety. In conclusion, ANS responses and facial expressions indicate that sensory specific satiety of foods 1) not only reduces the food’s pleasantness but also arousal and 2) are possibly mediated by changes in food emotions.
2017
16 citations
Object Extent Pooling for Weakly Supervised Single-Shot Localization
A. Gudi, N. van Rosmalen, M. Loog, J. van Gemert
In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak supervision is very valuable. However, the computational cost of generating and evaluating region proposals is heavy. We adapt the concept of Class Activation Maps into the very first weakly-supervised ‘single-shot’ detector that does not require the use of region proposals. To facilitate this, we propose a novel global pooling technique called Spatial Pyramid Averaged Max pooling for training this CAM-based network for object extent localization with only weak image-level supervision. We show this global pooling layer possesses a near ideal flow of gradients for extent localization, that offers a good trade-off between the extremes of max and average pooling. Our approach only requires a single network pass and uses a fast-backprojection technique, completely omitting any region proposal steps. To the best of our knowledge, this is the first approach to do so. Due to this, we are able to perform inference in real-time at 35fps, which is an order of magnitude faster than all previous weakly supervised object localization frameworks.