Collaboration to improve cross-race face identification: Wisdom of the multi-racial crowd?

Abstract

Face identification is particularly prone to error when individuals identify people of a race other than their own - a phenomenon known as the other-race effect (ORE). Here, we show that collaborative "wisdom-of-crowds" decision-making substantially improves face identification accuracy for own- and other-race faces over individuals working alone. In two online experiments, East Asian and White individuals recognized own- and other-race faces as individuals and as part of a collaborative dyad. Collaboration never proved more beneficial in a social setting than when individual identification decisions were combined computationally. The reliable benefit of non-social collaboration may stem from its ability to avoid the potential negative outcomes of group diversity such as conflict. Consistent with this benefit, the racial diversity of collaborators did not influence either general or race-specific face identification accuracy. Our findings suggest that collaboration between two individuals is a promising strategy for improving cross-race face identification that may translate effectively into forensic and eyewitness settings.

Keywords: collaboration; face-identity matching; group diversity; other-race effect; wisdom-of-crowds.

FIGURE 1

Experiments 1 and 2: stimuli of White (top panel) and East Asian (bottom panel) same-identity pairs (left panel), and different-identity pairs (right panel).

FIGURE 2

Face-identification accuracy for own- and other-race faces. Accuracy (AUC) results for East Asian participants (yellow) and White participants (blue). East Asian participants had a greater identification accuracy for East Asian faces compared to White faces. White participants had comparable accuracy for White faces and East Asian faces. Error bars represent 95% confidence intervals.

FIGURE 3

Face-identification accuracy (AUC) for individuals, social dyads, and non-social dyads. Social and non-social dyad accuracy was greater than individual performance. There were no performance differences between social and non-social collaboration. Error bars represent 95% confidence intervals.

FIGURE 4

Collaboration benefits for own- and other-race faces collapsed across collaboration type (social and non-social collaboration). Face-identification accuracy for East Asian individuals (yellow), East Asian dyads (dark yellow), White individuals (blue) and White dyads (dark blue) on own- and other race faces. Collaboration improved accuracy for both East Asian and White individuals for both race face stimulus. Error bars represent 95% confidence intervals.

FIGURE 5

Overall accuracy for different-race (East Asian/White) and same-race dyads (East Asian/East Asian and White/White) was comparable. Error bars represent 95% confidence intervals.

FIGURE 6

Accuracy for different-race (East Asian/White) and same-race dyads (East Asian/East Asian and White/White) on White (blue) and East Asian (yellow) faces. This shows that differences across dyad race depend on the stimulus race. East Asian same-race dyads have greater accuracy for same-race faces, but this is not true for White same-race dyads. For White dyads accuracy is also greater for East Asian faces. Error bars represent 95% confidence intervals.

FIGURE 7

Collaboration benefits for overall accuracy. Both non-social dyads and social dyads had greater identification accuracy than individuals. In addition, non-social dyads had greater identification accuracy than social dyads. Error bars represent 95% confidence intervals.