Bias amplification in experimental social networks is reduced by resampling

Large-scale social networks are thought to contribute to polarization by amplifying people's biases. However, the complexity of these technologies makes it difficult to identify the mechanisms responsible and to evaluate mitigation strategies. Here we show under controlled laboratory conditions that information transmission through social networks amplifies motivational biases on a simple perceptual decision-making task. Participants in a large behavioral experiment showed increased rates of biased decision-making when part of a social network relative to asocial participants, across 40 independently evolving populations. Drawing on techniques from machine learning and Bayesian statistics, we identify a simple adjustment to content-selection algorithms that is predicted to mitigate bias amplification. This algorithm generates a sample of perspectives from within an individual's network that is more representative of the population as a whole. In a second large experiment, this strategy reduced bias amplification while maintaining the benefits of information sharing. For example, social networks often lead to "echo-chambers" of like-minded individuals In this paper, we use an experimental paradigm to study how information sharing affects bias in judgment and decision-making. This new experimental paradigm allowed us to evaluate a mathematical theory of bias amplification and test a mitigation strategy based on this theory. Participants received a monetary reward for every correct answer. However, certain participants were offered an additional monetary reward for every green or blue dot in each stimulus ("motivated color" was randomized across participants, Our experimental paradigm consisted of arranging participants into an ordered set of groups, called "waves". At each wave t participants in social conditions observed judgments made by the participants in wave t 1. Participants in asocial conditions did not observe any social information. Each colored circle at the top of the image represents a participant. Stimuli consisted of 100 randomly positioned and sized blue and green dots displayed for one second. After viewing a stimulus, participants indicated whether they thought the stimulus had more green or more blue dots. Participants received feedback after each judgment on practice trials, and at the end of the experiment on test trials. All participants received a bonus on every trial if their judgment was correct. Participants in motivated conditions (shown here) received an additional bonus on every trial for every dot of their motivated color (green in both plots) regardless of whether their judgment was correct.