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.
2013
5 citations
Positive Affective Interactions: The Role of Repeated Exposure and Copresence
Shahid, Krahmer, Neerincx, Swerts
We describe and evaluate a new interface to induce positive emotions in users: a digital, interactive adaptive mirror. We study whether the induced affect is repeatable after a fixed interval (Study 1) and how copresence influences the emotion induction (Study 2). Results show that participants systematically feel more positive after an affective mirror session, that this effect is repeatable, and stronger when a friend is copresent.
2012
35 citations
Measuring learners’ co-occurring emotional responses during their interaction with a pedagogical agent in MetaTutor
Harley, Bouchet, Azevedo
This paper extends traditional emotional measurement frameworks in Intelligent Tutoring Systems by examining co-occurring emotions through a novel methodological approach. The study analyzed the occurrence of students’ embodiment of basic single discrete emotions and COEs, in addition to neutral states, using the automatic facial expression recognition program FaceReader 4.0. Focusing on the sub-goal setting task during learners’ interaction with MetaTutor, where a pedagogical agent assisted students in setting three relevant sub-goals for their learning session, results indicated that neutral and sadness were the most experienced SDEs and the most represented emotions in COE pairs. COEs accounted for nearly a quarter of students’ embodied emotions.
2012
56 citations
UX_Mate: From Facial Expressions to UX Evaluation
Staiano, Menéndez, Battocchi, De Angeli, Sebe
In this paper, the authors propose and evaluate UX_Mate, a non-invasive system for the automatic assessment of User eXperience . Additionally, they contribute a novel database of annotated and synchronized videos of interactive behavior and facial expressions. UX_Mate is a modular system that tracks users’ facial expressions, interprets them based on pre-set rules, and generates predictions about the occurrence of target emotional states, which can be linked to interaction events. The system simplifies UX evaluation by providing indications of event occurrences. UX_Mate offers several advantages over other state-of-the-art systems: easy deployment in the user’s natural environment, avoidance of invasive devices, and significant cost reduction. The paper reports on a pilot and a validation study involving a total of 46 users, where UX_Mate was used to identify interaction difficulties. The studies show encouraging results that open possibilities for automatic real-time UX evaluation in ecological environments.
2012
27 citations
Recognition of Emotional Facial Expressions: The Role of Facial and Contextual Information in the Accuracy of Recognition
Chóli & Fernández-Abascal
Recognition of emotional facial expressions is a central area in the psychology of emotion. This study presents two experiments. The first experiment analyzed recognition accuracy for basic emotions including happiness, anger, fear, sadness, surprise, and disgust. Thirty pictures were displayed to 96 participants to assess recognition accuracy. The results showed that recognition accuracy varied significantly across emotions. The second experiment analyzed the effects of contextual information on recognition accuracy. Information congruent and not congruent with a facial expression was displayed before presenting pictures of facial expressions. The results of the second experiment showed that congruent information improved facial expression recognition, whereas incongruent information impaired such recognition.
2012
536 citations
Emotion-Induced Engagement in Internet Video Advertisements
Teixeira, Wedel, Pieters
This study demonstrates how advertisers can utilize emotion and attention to engage consumers with Internet video advertisements. Through a controlled experiment, the authors evaluated joy and surprise using automated facial expression detection across a sample of ads. They measured attention concentration via eye tracking and assessed viewer retention by monitoring zapping behavior. This approach enabled testing predictions about the interplay between these emotions and individual attention differences during exposure. Findings indicate that both surprise and joy effectively focus attention and retain viewers. Notably, the intensity of surprise has a greater impact on attention concentration than its rate of change , whereas the velocity of joy influences viewer retention more than its level. Additionally, the effect of joy is asymmetric, with increases yielding higher gains than decreases result in losses. Based on these insights, the authors developed representative emotion trajectories to aid in ad design and testing.
2012
16 citations
Behavioural and physiological responses to two food odours
He, Boesveldt, de Graaf, de Wijk
Consumer food choice and intake are largely controlled by unconscious processes, which may be reflected better by implicit physiological and behavioural measures than by the more traditional explicit sensory tests. In this study, 26 human participants were exposed to an orange (pleasant) and a fish (unpleasant) odour presented in three different concentrations perceived as weak, medium and strong intensity, and five replications in a semi-random order via an olfactometer (Burghart OM2). Reactions to these odours were measured implicitly by means of facial expressions (automatically analysed with FaceReader), skin conductance responses and heart rate frequency (automatically analysed by Biolab), and explicitly with pleasantness ratings. Facial expressions reflected the odour’s valence (71% explained variance) and ranged from neutral (orange) to sadness/disgust/anger (fish) but showed additional differentiation with respect to odour intensity (15% explained variance). Skin conductance responses were largest for the unpleasant odour (p < 0.05), but showed no intensity effect. The unpleasant odour resulted in increased heart rate whereas the pleasant odour resulted in reduced heart rate (p < 0.05). The heart rate effects increased with intensity (p < 0.05). Different degrees of exposure were reflected in the implicit behavioural and physiological tests but not in the explicit pleasantness test. In summary, implicit physiological and behavioural responses provide detailed information on specific food odours that may not be provided by other more explicit tests.