Spontaneous first impressions emerge from brief training

Abstract

People have a strong and reliable tendency to infer the character traits of strangers based solely on facial appearance. In five highly powered and pre-registered experiments, we investigate the relative merits of learning and nativist accounts of the origins of these first impressions. First, we test whether brief periods of training can establish consistent first impressions de novo. Using a novel paradigm with Greebles-a class of synthetic object with inter-exemplar variation that approximates that seen between individual faces-we show that participants quickly learn to associate appearance cues with trustworthiness (Experiments 1 and 2). In a further experiment, we show that participants easily learn a two-dimensional structure in which individuals are presented as simultaneously varying in both trustworthiness and competence (Experiment 3). Crucially, in the final two experiments (Experiments 4 and 5) we show that, once learned, these first impressions occur following very brief exposure (100 ms). These results demonstrate that first impressions can be rapidly learned and, once learned, take on features previously thought to hold only for innate first impressions (rapid availability). Taken together, these results highlight the plausibility of learning accounts of first impressions.

Figure 1

(a) The familiar and novel Greebles used in Experiments 1, 2, and 4. (b) Example display from a training trial. (c) Example display from a test trial. (d) Results from Experiment 1. (e) Results from Experiment 2. Error bars represent 95% confidence intervals around the mean. Stimulus images courtesy of Michael J. Tarr, Carnegie Mellon University, http://www.tarrlab.org/.

Figure 2

The 24 Greebles used in Experiments 3 and 5 included exemplars from two genders and two families. Stimulus images courtesy of Michael J. Tarr, Carnegie Mellon University, http://www.tarrlab.org/.

Figure 3

(a) Results from Experiment 3, judgements of trustworthiness. (b) Results from Experiment 3, judgements of competence. Error bars represent 95% confidence intervals around the mean.

Figure 4

Trial structure in Experiment 4. Stimulus images courtesy of Michael J. Tarr, Carnegie Mellon University, http://www.tarrlab.org/.

Figure 5

Results from Experiment 4. Error bars represent 95% confidence intervals around the mean.

Figure 6

(a) Results from Experiment 5, judgements of trustworthiness. (b) Results from Experiment 5, judgements of competence. Error bars represent 95% confidence intervals around the mean.