Testing differential use of payoff-biased social learning strategies in children and chimpanzees

Abstract

Various non-human animal species have been shown to exhibit behavioural traditions. Importantly, this research has been guided by what we know of human culture, and the question of whether animal cultures may be homologous or analogous to our own culture. In this paper, we assess whether models of human cultural transmission are relevant to understanding biological fundamentals by investigating whether accounts of human payoff-biased social learning are relevant to chimpanzees (Pan troglodytes). We submitted 4- and 5-year-old children (N = 90) and captive chimpanzees (N = 69) to a token-reward exchange task. The results revealed different forms of payoff-biased learning across species and contexts. Specifically, following personal and social exposure to different tokens, children's exchange behaviour was consistent with proportional imitation, where choice is affected by both prior personally acquired and socially demonstrated token-reward information. However, when the socially derived information regarding token value was novel, children's behaviour was consistent with proportional observation; paying attention to socially derived information and ignoring their prior personal experience. By contrast, chimpanzees' token choice was governed by their own prior experience only, with no effect of social demonstration on token choice, conforming to proportional reservation. We also find evidence for individual- and group-level differences in behaviour in both species. Despite the difference in payoff strategies used, both chimpanzees and children adopted beneficial traits when available. However, the strategies of the children are expected to be the most beneficial in promoting flexible behaviour by enabling existing behaviours to be updated or replaced with new and often superior ones.

Keywords: cultural transmission bias; culture; payoff bias; social learning; social learning strategies.

Figure 1.

Parts (a–c) relate to children, while parts (d–f) relate to chimpanzees in experiment 1. Parts (a) and (d) show samples from the posterior distribution of coefficient values associated with the personal and social predictor variables. The cloud of points is consistent with the β mean, s.d. and HDPI values reported in the text. The cross-hairs distinguish positive and negative values. Parts (b,c) and (c,d) show the predicted proportion of T_social exchanges during the test phase by simulated individuals whose behaviour is generated by sampling from the posterior distribution of the Schlag rules model. In parts (b) and (e) each individual simulation samples from the posterior distribution for an average intercept. By contrast, in parts (c) and (f), each individual simulation samples from the posterior distribution for an average intercept and in addition, from the posterior variation in individual- and group-level intercepts. Blue lines represent females and purple lines males. The thick lines show the behaviour of an average simulated individual. For each simulated individual, sampled parameter values are held constant across the three conditions indicated on the horizontal axis. (Online version in colour.)

Figure 2.

Samples from the posterior distribution of coefficient values associated with the personal and social predictor variables in (a) children and (b) chimpanzees in experiment 2. The cross-hairs distinguish positive and negative values.