ArticlePDF Available

Interpretation of Appearance: The Effect of Facial Features on First Impressions and Personality

Authors:

Abstract and Figures

Appearance is known to influence social interactions, which in turn could potentially influence personality development. In this study we focus on discovering the relationship between self-reported personality traits, first impressions and facial characteristics. The results reveal that several personality traits can be read above chance from a face, and that facial features influence first impressions. Despite the former, our prediction model fails to reliably infer personality traits from either facial features or first impressions. First impressions, however, could be inferred more reliably from facial features. We have generated artificial, extreme faces visualising the characteristics having an effect on first impressions for several traits. Conclusively, we find a relationship between first impressions, some personality traits and facial features and consolidate that people on average assess a given face in a highly similar manner.
Content may be subject to copyright.
A preview of the PDF is not available
... Facial features are mainly used for identification, authentication and help to judge the nature of human characteristics. Extracting the facial features helps in identifying the character of a person [12,28]. This statement is mainly evident from the fact that "Face is the index of mind". ...
Article
Full-text available
Human character is the collection of actions, qualities and habits, which differentiate one individual from the other. In humans, characters are the inborn features and it is responsible for every human behaviors or activity is done in the environment. The identification of the original character of an individual is complex. To extract effective features and constructing a novel robust classifier still remains a major challenge in this area. In this work, the authors aimed at developing a deep learning-based human character identification model using facial features. Initially, preprocessing takes place by weighted bilateral filter (WBF) to swipe up the unwanted distortions, scarcities and the background of an image. Along with this, the feature extraction process is agonized to extract the facial feature to precisely classify the character based on the Viola-Jones algorithm (VJA). Based on facial features, the character of the person can be identified with the deep learning approaches. Thus, this work mainly focused on identifying the human characters based on the deep convolutional neural network-Rain fall optimization (DCRNN) model under four strategies namely, Sanguine (oblong face), Choleric (square face), Phlegmatic (heart face) and Melancholic (round face) with high accuracy and efficiency. The performance of the proposed model is finally validated with existing methods of CNN, DCNN, inception CNN, SVM, SVM-RBF, SVM-LF, KNN and PNN in terms of accuracy, precision, recall, specificity, f-measure, MAE, RMSE and PCC. The proposed model procures a performance of 96%, 94%, 98%, 95%, 0.07, 0.15 and 94% respectively due to the incorporation of RFO with DCNN model for fine tuning and diminishing the error functions. Along with this, the statistical analysis of Wilcoxon and Friedman test are also evaluated and attains a best outcome.
... Character appearance has significant contributions to the overall judgement and perception of virtual characters and agents [14,61,70]. We ensured that clothing, eye color and eyebrow shape were homogenized between characters, as previous works show that clothing [38] and facial features [33,41,65] influence the perception of personality traits. In our appearance-only experiment (Section 4.2), we test the perceived personality across our chosen character appearances. ...
Conference Paper
The portrayed personality of virtual characters and agents is understood to influence how we perceive and engage with digital applications. Understanding how the features of speech and animation drive portrayed personality allows us to intentionally design characters to be more personalized and engaging. In this study, we use performance capture data of unscripted conversations from a variety of actors to explore the perceptual outcomes associated with the modalities of speech and motion. Specifically, we contrast full performance-driven characters to those portrayed by generated gestures and synthesized speech, analysing how the features of each influence portrayed personality according to the Big Five personality traits. We find that processing speech and motion can have mixed effects on such traits, with our results highlighting motion as the dominant modality for portraying extraversion and speech as dominant for communicating agreeableness and emotional stability. Our results can support the Extended Reality (XR) community in development of virtual characters, social agents and 3D User Interface (3DUI) agents portraying a range of targeted personalities.
... In [6], the authors studied and proposed the key facial features that have an import impact on people's first impression. We can draw at least four valid inferences from other people's facial features [7]. Reference [8] examined the relationship between self-reported personality traits and first impressions. ...
Article
Full-text available
The assessment of personality traits is now a key part of many important social activities, such as job hunting, accident prevention in transportation, disease treatment, policing, and interpersonal interactions. In a previous study, we predicted personality based on positive images of college students. Although this method achieved a high accuracy, the reliance on positive images alone results in the loss of much personality-related information. Our new findings show that using real-life 2.5D static facial contour images, it is possible to make statistically significant predictions about a wider range of personality traits for both men and women. We address the objective of comprehensive understanding of a person's personality traits by developing a multiperspective 2.5D hybrid personality-computing model to evaluate the potential correlation between static facial contour images and personality characteristics. Our experimental results show that the deep neural network trained by large labeled datasets can reliably predict people's multidimensional personality characteristics through 2.5D static facial contour images, and the prediction accuracy is better than the previous method using 2D images.
Chapter
Whenever we meet individuals face to face, we interface with their assumed behavioral disposition. Our brain continuously gathers data where our knowledge, perceptions and classification data are in our head which is commonly termed as intuition. Whenever humans classify data, it passes off as human judgment. The human face provides the most significant clue to a person’s emotional state. With the advancement of artificial intelligence, these states can be coded using a neural net where the judgment can be obtained using a automatic decision support system. With machine learning, a predefined pattern classifier engine can learn the facial patterns. These can be used to arrive at an augmented deciphered pattern and animated on a computer to predict future behavior. This can enable people to get a clearer insight into the implications of their decisions. KeywordsPattern recognitionPerceptual insightClassifierDecision support engine
Chapter
This module contains a principal dataset collated from various open data, which we previously identified as not containing identifying information. This principal dataset is generated to be a pseudo-population to generate smaller sample datasets from without identifying information. These sample datasets will be used to generate precision estimates (α and 1-α) for algorithms to check for identifying information in open data in a next step. The principal dataset shared here contains 30,251 rows and a maximum of 23 columns.
Article
Full-text available
Background The COVID-19 pandemic has necessitated masking in public spaces. Masks cover the wearer’s face partially and thus may impact the perceived attractiveness of individuals and hence, interpersonal relations. Objective To determine if facial coverings affect attractiveness. Methods An online survey was conducted using 114 headshot images, two each- unmasked and masked- of 57 individuals. 207 participants rated them on an ordinal scale from 1 (least attractive) to 10 (most attractive). Parametric and non-parametric tests were performed, as appropriate, for comparison. Results For the first quartile, the average rating increased significantly when wearing a mask (5.89 ± 0.29 and 6.54 ± 0.67; p = 0.01). For control images ranked within the fourth quartile, the average rating decreased significantly when wearing a mask (7.60 ± 0.26 and 6.62 ± 0.55; p <0.001). In the female sub-group (n= 34), there was a small increase in average rating when masked, while in the male sub-group (n = 23), there was a small decrease in average rating when masked, but the change was not statistically significant (p > 0.05). For unmasked female images ranked within the first quartile, the average rating increased significantly when wearing a mask (5.77 ± 0.27 and 6.76 ± 0.36; p = 0.001). For the female sub-group with mean ratings within the fourth quartile, the average decreased significantly when wearing a medical mask (7.53 ± 0.30 and 6.77 ± 0.53; p < 0.05). For unmasked male images ranked within the first quartile, the average rating increased when wearing a medical mask but the change was not statistically significant (p > 0.05) whereas for the control male images within the fourth quartile, the average rating decreased significantly when masked (7.72 ± 0.18 and 6.50 ± 0.54; p < 0.05). Conclusions While wearing a facial covering significantly increased attractiveness for images less attractive at baseline, and decreased attractiveness for those that are more attractive at baseline; it did not cause a significant overall change in attractiveness in the study population.
Article
Impressions from faces are made remarkably quickly and they can underpin behaviour in a wide variety of social contexts. Over the last decade many studies have sought to trace the links between facial cues and social perception and behaviour. One such body of work has shown clear overlap between the fields of face perception and social stereotyping by demonstrating a role for conceptual stereotypes in impression formation from faces. We integrate these results involving conceptual influences on impressions with another substantial body of research in visual cognition which demonstrates that much of the variance in impressions can be predicted from perceptual, data‐driven models using physical cues in face images. We relate this discussion to the phylogenetic, cultural, individual and developmental origins of facial impressions and define priority research questions for the field including investigating non‐WEIRD cultures, tracking the developmental trajectory of impressions and determining the malleability of impression formation.
Chapter
This chapter provides an insight into the psychosocial consequences of facial palsy. Following an overview of various research in this field, we describe the psychosocial consequences for patients with a facial palsy. Besides experiencing negative physical side effects or complications, such as incomplete eye closure, limited mouth movement, and/or synkinesis, patients also can have a mental burden. Although outcome of research varies, it is clear that facial palsy has a severe impact on quality of life. Besides a description of feelings of fear and depression, we also focus on coping and how to deal with the problems of a facial palsy. We conclude with recommendations for patients, their social environment, and health care professionals.
Article
Full-text available
The ability to accurately assess the intelligence of other persons finds its place in everyday social interaction and should have important evolutionary consequences. We used static facial photographs of 40 men and 40 women to test the relationship between measured IQ, perceived intelligence, and facial shape. Both men and women were able to accurately evaluate the intelligence of men by viewing facial photographs. In addition to general intelligence, figural and fluid intelligence showed a significant relationship with perceived intelligence, but again, only in men. No relationship between perceived intelligence and IQ was found for women. We used geometric morphometrics to determine which facial traits are associated with the perception of intelligence, as well as with intelligence as measured by IQ testing. Faces that are perceived as highly intelligent are rather prolonged with a broader distance between the eyes, a larger nose, a slight upturn to the corners of the mouth, and a sharper, pointing, less rounded chin. By contrast, the perception of lower intelligence is associated with broader, more rounded faces with eyes closer to each other, a shorter nose, declining corners of the mouth, and a rounded and massive chin. By contrast, we found no correlation between morphological traits and real intelligence measured with IQ test, either in men or women. These results suggest that a perceiver can accurately gauge the real intelligence of men, but not women, by viewing their faces in photographs; however, this estimation is possibly not based on facial shape. Our study revealed no relation between intelligence and either attractiveness or face shape.
Article
Full-text available
High facial width-to-height ratio (fWHR) has been associated with a cluster of behavioural traits in men, including aggression and status-striving. This association between face structure and behaviour may be caused by testosterone. Here we investigated the relationship of both baseline and reactive testosterone levels to fWHR. In addition, we investigated the link between testosterone and three well-characterised sexually dimorphic facial metrics. Testosterone was measured in one sample of males (n = 185) before and after a speed-dating event. An additional sample provided only baseline testosterone measures (n = 92). fWHR was positively associated with testosterone reactions to potential mate exposure and marginally associated with baseline testosterone in Sample 1. We found a positive association with baseline testosterone and fWHR in Sample 2. In addition, face-width-to-lower-height ratio was positively associated with testosterone in both samples, suggesting that, in particular, facial width (scaled by two measures of facial height) is associated with testosterone. Importantly, our results also indicate that there is no association between adult testosterone and the sexual dimorphism of face shape. Thus, while our findings question the status of sexual dimorphism as a proxy measure of testosterone, they do provide evidence that testosterone is linked to fWHR and might underlie the relationship between fWHR and behaviour.
Article
Full-text available
The facial width-to-height ratio (fWHR) has been identified as a reliable predictor of men's behavior, with researchers focusing on evolutionary selection pressures as the underlying mechanism explaining these relationships. In this paper, we complement this approach and examine the extent to which social processes also determine the extent to which men's fWHR serves as a behavioral cue. Specifically, we propose that observers' treatment of target men based on the targets' fWHR subsequently affects behavior, leading the targets to behave in ways that are consistent with the observers' expectations (i.e., a self-fulfilling prophecy). Results from four studies demonstrate that individuals behave more selfishly when interacting with men with greater fWHRs, and this selfish behavior, in turn, elicits selfish behavior in others.
Article
This article presents a four-category framework to characterize the contents of prescriptive gender stereotypes. The framework distinguishes between prescriptions and proscriptions that are intensified by virtue of one's gender, and those that are relaxed by virtue of one's gender. Two studies examined the utility of this framework for characterizing prescriptive gender stereotypes in American society (Study 1) and in the highly masculine context of Princeton University (Study 2). The results demonstrated the persistence of traditional gender prescriptions in both contexts, but also revealed distinct areas of societal vigilance and leeway for each gender. In addition, they showed that women are seen more positively, relative to societal standards, than are men. We consider the implications of this framework for research on reactions to gender stereotype deviants and sex discrimination.
Article
Three studies demonstrate the warm glow heuristic (Monin, 2003) without relying on aggregated ratings, and illustrate the important distinction between correlating average ratings versus averaging individual correlations. In Study 1, we re-analyze previous data correlating individual ratings with aggregates from another small sample of raters. In Study 2, we correlate individual familiarity ratings with normed attractiveness from a large sample of raters (n > 2, 500). Study 3 bypasses the issue of aggregates altogether by having participants provide both attractiveness and familiarity ratings and computing correlations within participants. Despite this more conservative approach, the results of all three studies support the existence of the beautiful-is-familiar phenomenon.
Article
In addition to signaling identity, sex, age, and emotional state, people frequently use facial characteristics as a basis for personality attributions. Typically, there is a high degree of consensus in the attributions made to faces. Nevertheless, the extent to which such judgments are veridical is unclear and somewhat controversial. We have examined the relationship between self-report and perceived personality using both faces of individuals and computer graphic composites. Photographs were taken of 146 men and 148 women who each also completed a self-report personality questionnaire from which scores on the big five personality dimensions were derived. In study 1, we identified a relationship between self-reported extraversion and perceived extraversion in individual faces. For male faces alone, we also found some accuracy in the perception of emotional stability and openness to experience. In study 2, composite faces were made from individuals self-reporting high and low scores on each of the five dimensions. These composites were rated for personality and attractiveness by independent raters. Discriminant analyses indicated that, controlling for attractiveness, independent ratings on congruent personality dimensions were best able to discriminate between composite faces generated from individuals high or low on the self-report dimensions of agreeableness, extraversion, and, for male faces only, emotional stability.
Article
Three experiments are presented that investigate the two-dimensional valence/trustworthiness by dominance model of social inferences from faces (Oosterhof & Todorov, 2008). Experiment 1 used image averaging and morphing techniques to demonstrate that consistent facial cues subserve a range of social inferences, even in a highly variable sample of 1000 ambient images (images that are intended to be representative of those encountered in everyday life, see Jenkins, White, Van Montfort, & Burton, 2011). Experiment 2 then tested Oosterhof and Todorov's two-dimensional model on this extensive sample of face images. The original two dimensions were replicated and a novel 'youthful-attractiveness' factor also emerged. Experiment 3 successfully cross-validated the three-dimensional model using face averages directly constructed from the factor scores. These findings highlight the utility of the original trustworthiness and dominance dimensions, but also underscore the need to utilise varied face stimuli: with a more realistically diverse set of face images, social inferences from faces show a more elaborate underlying structure than hitherto suggested.
Article
A Monte-Carlo simulation was conducted to assess the extent that a correlation estimate can be inflated when an average-based measure is used in a commonly employed correlational design. The results from the simulation reveal that the inflation of the correlation estimate can be substantial, up to 76%. Additionally, data was re-analyzed from two previously published studies to determine the extent that the correlation estimate was inflated due to the use of an averaged based measure. The re-analyses reveal that correlation estimates had been inflated by just over 50% in both studies. Although these findings are disconcerting, we are somewhat comforted by the fact that there is a simple and easy analysis that can be employed to prevent the inflation of the correlation estimate that we have simulated and observed.