Modelling perceptions of criminality and remorse from faces using a data-driven computational approach

Caring or daring? Exploring the impact of facial masculinity/femininity and gender category information on first impressions

“…This impact of facial masculinity/femininity persisted even though much more distinct and likewise visibly perceived information, that is, gender category information was provided. The finding that facial features strongly impacted personality ascriptions fits well into existing literature showing that people base diverse social judgments of others on subtle facial information, for example, about sexual orientation [49], political orientation [50], morality [51], criminality [52], or central personality dimensions [21]. …”

“…So, exactly the same sort and amount of information was manipulated in all faces. This method has been shown to generalize across participants and faces before [16,21,51,52]. Secondly, the statistical method we applied to analyze our data, namely the linear mixed models analyses included random effects for participants and faces.…”

First Impressions: A Survey on Vision-Based Apparent Personality Trait Analysis

“…First impressions also influence legal decisionmaking [25]. Nevertheless, at the same time that different research communities (e.g., machine learning, computer vision and psychology) are advancing the state-of-the-art in the field in different directions, it was recently observed 1 that some Artificial Intelligence based models are exhibiting racial and gender biases, which are considered extremely complex and emerging issues.…”

“…Even though the problem of stereotyping is minimized in [28] (which could bias the analysis) through the usage of manipulated faces (synthetic faces are used in [23], [25] for the same purpose), it should be noted that social judgments in real situations are formed from different sources, such as pose, gaze, facial expression or styling. For example, hairstyle, which is extrafacial information, can be intentionally chosen by target persons to shape others' impressions of them.…”

Contributions of shape and reflectance information to social judgments from faces

“…People make face-based inferences, such as aggressiveness and trustworthiness, about others even after brief exposure to their faces (Bar, Neta, & Linz, 2006;Borkenau, Brecke, Möttig, & Paelecke, 2009;Rule, Ambady, & Adams, 2009;Todorov, Loehr, & Oosterhof, 2010;Todorov, Pakrashi, & Oosterhof, 2009;Willis & Todorov, 2006), and these inferences affect social interactions (for reviews, see Todorov, 2017;Todorov, Mende-Siedlecki, & Dotsch, 2013;Todorov et al, 2015;Todorov, Said, & Verosky, 2011). Although computational models of facial social judgments have been built and validated (Funk, Walker, & Todorov, 2016;Oh, Buck, & Todorov, 2019;Oh, Dotsch, Porter, & Todorov, 2019;Oosterhof & Todorov, 2008;Todorov & Oosterhof, 2011;Walker, Jiang, Vetter, & Sczesny, 2011;Walker & Vetter, 2009, how shape and reflectance information contribute to social judgments has not been systematically investigated.…”