Hybrid social learning in human-algorithm cultural transmission

Abstract

Humans are impressive social learners. Researchers of cultural evolution have studied the many biases shaping cultural transmission by selecting who we copy from and what we copy. One hypothesis is that with the advent of superhuman algorithms a hybrid type of cultural transmission, namely from algorithms to humans, may have long-lasting effects on human culture. We suggest that algorithms might show (either by learning or by design) different behaviours, biases and problem-solving abilities than their human counterparts. In turn, algorithmic-human hybrid problem solving could foster better decisions in environments where diversity in problem-solving strategies is beneficial. This study asks whether algorithms with complementary biases to humans can boost performance in a carefully controlled planning task, and whether humans further transmit algorithmic behaviours to other humans. We conducted a large behavioural study and an agent-based simulation to test the performance of transmission chains with human and algorithmic players. We show that the algorithm boosts the performance of immediately following participants but this gain is quickly lost for participants further down the chain. Our findings suggest that algorithms can improve performance, but human bias may hinder algorithmic solutions from being preserved. This article is part of the theme issue 'Emergent phenomena in complex physical and socio-technical systems: from cells to societies'.

Keywords: cultural evolution; human–machine collaboration; social learning; transmission chain.

Figure 1.

(a) In the first stage of the task, participants saw an animation of the solution entered by the previous player (left-hand side). A snapshot showing the transition from node E to node C is depicted. In the second stage, the participants could enter a path by clicking on the respective nodes in sequence (centre). The node with grey background colour indicates the current node the participant is in. In the last stage, the total score of the player’s sequence is revealed (right-hand side). The network presented here is classified as human-regretful. (b) For each environment class, we constructed two chains of eight generations of players. In hybrid chains, the second generation player was replaced by an algorithm. The networks depict the solutions of the first four generations as well as the last generation for a selected environment (corresponding to (a)). The integer on the arrows denotes the step at which a player was choosing the move. The cumulative reward is shown in the upper right corner of each graphic. In this example, for the human-only chain the cumulative reward increases at first, but quickly reaches a plateau. For the hybrid chain, the algorithm shows a performance greater than observed in the human-only chain, but this improvement gets lost over subsequent human generations. (Online version in colour.)

Figure 2.

(a) Difference in performance between conditions (hybrid—human-only); (inset) performance improvement over generations within human-only chains in relation to the first generation; (b) average number of actions of solutions that match those of generation 2 within the same chain; (c) maximum-likelihood estimates of the pruning parameter for human-only chains; (d) difference of the maximum-likelihood estimates of the pruning parameter between conditions (hybrid—human-only). All panels share the same colour code. Vertical bars are indicating bootstrapped 95% confidence intervals. A dashed vertical line shows the algorithm’s position. (Online version in colour.)

Figure 3.

Average reward of the solutions of 100 000 modelled agents. Human-only chains are depicted in blue, algorithm-only in orange, hybrid chains with a single algorithm (as in the experiment) in green and randomly mixed hybrid chains in red. On the left panel the environment favours the algorithmic bias, on the right panel it favours the human bias. We compare two type of content bias, one with a bias for higher performing solutions (solid) and a second with an additional bias to match the specific bias of the agent. A dashed vertical line shows the algorithm’s position in the single-algorithm condition. (Online version in colour.)