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.
2024
42 citations
The effects of online facial muscle training with resonance vocalization on mental health in postpartum women: A single-arm pilot study
R. Okamoto, E. Terasawa, A. Usui, M. Matsushima, H. Okayama
Leveraging FaceReader technology, in the future, intervention studies with a higher evidence level, such as a crossover randomized controlled trial, are required.
Tags
2024
2 citations
Low sadness and high happiness facial prevalence to others’ suffering in intimate partner violence against women perpetrators: influence of emotional decoding deficits
J. Comes‐Fayos, Á. Romero‐Martínez, M. Lila, M. Martínez, L. Moya‐Albiol
The facial response to others’ emotions has been linked to adaptive social interactions. Interestingly, maladjusted emotional recognized as a significant risk factor for intimate partner violence against women (IPVAW). However, the of IPVAW perpetrators remains unclear. The present study analyzes the facial response, well self-reported emotions, ( n = 55) compared controls ( n = 48) during a violence-focused empathic induction task using “FaceReader” coding software. Additionally, we explored the influence of emotional decoding on their responsiveness. Compared controls, exhibited lower prevalence of sadness expression and higher happiness expressions during the task, along with reduced emotionality. Coherently, expression, tenderness. Finally, poorer belonging group explained expressions. Our findings provide further evidence supporting a distinctive pattern of others’ suffering in perpetrators. This provides promising direction to address occurrence by treating relevant socioaffective deficits, such as responsiveness or decoding.
2024
8 citations
FaceReader as a neuromarketing tool to compare the olfactory preferences of customers in selected markets
J. Berčík, A. Mravcová, E. Sendra, D. López‐Lluch, A. Farkaš
The purpose of this paper is to examine FaceReader as a tool to compare the olfactory preferences of customers in two selected countries. This paper examines the subconscious/unconscious perception of fragrances. In this case, it is not classical qualitative sensory testing but the perception of fragrances. The aim of the study is to identify associations of scents related to sales through images of aromas. A special platform was used to obtain implicit feedback, which allows online collection of implicit feedback using software 7. Findings: The authors noticed different moods respondents respond when they answered the question about what they associate with the smell of products. Respondents, can be explained by higher pleasant mood. The main contribution of the work lies in new opportunities that marketing research can rely not only on explicit but also implicit data. Extension of methodological apparatus presupposes some form of control of data collected by questionnaire. The use of biometric tools represent an efficient alternative in terms of time and money for selection/research of specific stores/departments. Research limitations/implications: It must be noted the sample is small, adequate conclusions cannot be made for the entire population. Based on empirical findings, pandemic-related limitations, plan to conduct similar real aroma samples even larger tested, considering weather, season, sensitivity (anosmia, hyposmia, normosmia) of participant and fatigue (beginning and end of week). Originality/value: Today, marketers are facing the greatest challenge how to attract consumers’ attention. Every individual has shopping environment based his own experience, beliefs and attitudes. That is why techniques and approaches becoming increasingly popular in environment.
2023
6 citations
Sludged! Can financial literacy shield against price manipulation at the shops?
T. West, D. Butler, L. Smith
In this research, FaceReader software is used to explore sludged! can financial literacy shield against price manipulation at the shops?, providing objective data on emotional responses and facial muscle activities.
2023
14 citations
Electromyographic Validation of Spontaneous Facial Mimicry Detection Using Automated Facial Action Coding
C. Hsu, W. Sato
Although electromyography (EMG) remains the standard, researchers have begun using automated facial action coding system (FACS) software to evaluate spontaneous mimicry despite a lack of evidence of its validity. Using EMG as a ground truth, we confirmed the detection of mimicry in the zygomaticus major (ZM) unit (AU12, lip corner puller) via an automated FACS. Participants were alternately presented with real-time model performance and prerecorded videos of dynamic expressions, while simultaneous ZM signal was acquired. Facial mimicry was estimated for AU12 using FaceReader, Py-Feat, and OpenFace. The FACS is less sensitive and accurate than EMG, but mimicking responses significantly correlated with EMG responses. All three programs detected enhanced facial mimicry by live performances. The time series showed roughly 100–300 ms latency relative to ZM. Our results suggested that although automated FACS could not replace EMG detection, it could serve a purpose for large effect sizes. Researchers should be cautious when studying outputs, especially when studying clinical populations. In addition, developers should consider validation of AU estimation as a benchmark.
2023
8 citations
You Look like You’ll Buy It! Purchase Intent Prediction Based on Facially Detected Emotions in Social Media Campaigns for Food Products
K. Tzafilkou, A. A. Economides, F. R. Panavou
Understanding the online behavior and purchase intent of consumers in social media can bring significant benefits to ecommerce business and consumer research community. Despite the tight links between emotions and purchase decisions, previous studies focused primarily on predicting through web analytics, sales, and historical data. Here, we use facially expressed emotions detected by FaceReader OnlineTM while watching video campaigns for food products (yogurt, nut butters) is suggested to infer consumer intent. A multi-stage experiment was set, collecting data from 154 valid sessions from 74 participants. A set of different classification models were deployed, and performance evaluation metrics were compared. The models included Neural Networks (NNs), Logistic Regression (LR), Decision Trees (DTs), Random Forest (RF), and Support Vector Machine (SVM). NNs proved highly accurate (90–91%) in predicting consumers’ intention to buy or try the product, while RF showed promising results (75%). Expressions of sadness and surprise indicated the highest levels of importance, with DTs correspondingly. Low arousal, micro expressions, might be sufficient input based on instances decoded emotions.