Reduction in social learning and increased policy uncertainty about harmful intent is associated with pre-existing paranoid beliefs: Evidence from modelling a modified serial dictator game

Abstract

Current computational models suggest that paranoia may be explained by stronger higher-order beliefs about others and increased sensitivity to environments. However, it is unclear whether this applies to social contexts, and whether it is specific to harmful intent attributions, the live expression of paranoia. We sought to fill this gap by fitting a computational model to data (n = 1754) from a modified serial dictator game, to explore whether pre-existing paranoia could be accounted by specific alterations to cognitive parameters characterising harmful intent attributions. We constructed a 'Bayesian brain' model of others' intent, which we fitted to harmful intent and self-interest attributions made over 18 trials, across three different partners. We found that pre-existing paranoia was associated with greater uncertainty about other's actions. It moderated the relationship between learning rates and harmful intent attributions, making harmful intent attributions less reliant on prior interactions. Overall, the magnitude of harmful intent attributions was directly related to their uncertainty, and importantly, the opposite was true for self-interest attributions. Our results explain how pre-existing paranoia may be the result of an increased need to attend to immediate experiences in determining intentional threat, at the expense of what is already known, and more broadly, they suggest that environments that induce greater probabilities of harmful intent attributions may also induce states of uncertainty, potentially as an adaptive mechanism to better detect threatening others. Importantly, we suggest that if paranoia were able to be explained exclusively by core domain-general alterations we would not observe differential parameter estimates underlying harmful-intent and self-interest attributions.

Fig 1. Log Likelihood values of the model.

(A) Computed mean log likelihoods for each trial, coloured by dictator type. (B) Density plots of log likelihood values for each trial, coloured by dictator type. Coloured lines represent group means (C) Computed mean log likelihoods for each GPTS score quantile and clinical score cut off (Green et al., 2008). (D) Density plots of log likelihood values for each trial across each GPTS score quantile and clinical score cut off (Green et al., 2008). (E) The association between GPTS scores (minimum score = 32) and loglikelihood values. Dots = mean loglikelihood value across that score of the GPTS. Lines = 95% confidence intervals. The grey line in each plot (at -4.394) represents the loglikelihood that would be observed if the model was capturing behaviour by chance.

Fig 2. Simulated Behavioural Data.

(A) Generated Harmful Intent (HI) attributions for simulated participants at each level of paranoia at each trial within fair and unfair dictators. Dots represent the mean for each level of paranoia. Lines represent the 95% confidence interval. (B) Generated density distributions for simulated participant HI attributions (red) for each trial (1–6) within unfair and fair dictators for each level of paranoia. (C) Generated Self-Interest (SI) attributions for simulated participants at each level of paranoia at each trial within fair and unfair dictators. Dots represent the mean for each level of paranoia. Lines represent the 95% confidence interval. (D) Generated density distributions for simulated participant SI attributions (blue) for each trial (1–6) within unfair and fair dictators for each level of paranoia. (E) Smoothed linear splines for both simulated participant harmful intent and self-interest attributions by prior paranoia (minimum score = 32).

Fig 3. Spearman rank correlations between uHI0, uSI0, uΠ, and η, and pre-existing paranoia and in-the-moment attributions.

(A) Quadratic fit for uncertainty of partner policies across the mean harmful intent attributions scored over 18 trials. (B) Quadratic fit for uncertainty of partner policies across the mean self-interest attributions scored over 18 trials. (C) Linear fit for uncertainty of partner policies across GPTS scores. (D) Quadratic fit of learning rate by mean attributions scored over 18 trials.

Fig 4. Mixed Graphical Models.

(A) Gaussian Graphical Model of latent parameters and prior paranoid beliefs. (B) Moderated Network Model between latent parameters when moderated over prior paranoia from low to high Z-scores (-0.85–4). Red edges = negative association; green edges = positive association.

Fig 5. Moderation effects of pre-existing paranoia on edges within the Moderated Network Model (Fig 4B).

The left panel displays the pairwise effects–the overall relationship between the parameters in the Gaussian Graphical Model of parameters—and the right panel shows the moderation effect of GPTS score on the pairwise effects–the influence of variable GPTS scores on the relationship between parameters. Both are shown with 95% confidence intervals of the bootstrapped sampling distributions. The number at the centre of the sampling distribution is the proportion of bootstrap samples in which a parameter has been estimated to be nonzero [26].

Fig 6. Mean partner policy depending on attributes.

Okra: preference for returning a large amount to the participant. Blue / purple: preference for returning very little.

Fig 7. Smoothed density distributions of the fitted parameters derived from the computational model.