Negativity-bias in forming beliefs about own abilities

Abstract

During everyday interactions people constantly receive feedback on their behavior, which shapes their beliefs about themselves. While classic studies in the field of social learning suggest that people have a tendency to learn better from good news (positivity bias) when they perceive little opportunities to immediately improve their own performance, we show updating is biased towards negative information when participants perceive the opportunity to adapt their performance during learning. In three consecutive experiments we applied a computational modeling approach on the subjects' learning behavior and reveal the negativity bias was specific for learning about own compared to others' performances and was modulated by prior beliefs about the self, i.e. stronger negativity bias in individuals lower in self-esteem. Social anxiety affected self-related negativity biases only when individuals were exposed to a judging audience thereby potentially explaining the persistence of negative self-images in socially anxious individuals which commonly surfaces in social settings. Self-related belief formation is therefore surprisingly negatively biased in situations suggesting opportunities to improve and this bias is shaped by trait differences in self-esteem and social anxiety.

Figure 1

Trial sequence, modeling of learning behavior, and experimental factors of the experiments. (A) A cue (CUE) in the beginning of each trial indicated the following estimation category. After providing their performance expectation ratings (EXP) participants received an estimation question (EST), followed by the corresponding performance feedback (FB). (B) EXP ratings were modeled by means of Rescorla-Wagner delta-rule update equations with different learning rates (α, see Methods) taking into account trial-by-trial prediction errors (PE_t) in response to the provided FB. (C) In three experiments we assessed the impact of two experimental factors. The “Agent” was manipulated within subjects in the Agent-LOOP task in experiments 1 and 3 and the “Audience” was manipulated in a between-subject design in the Audience-LOOP task (experiment 2) as well as between the Private and the Public group of the Agent-LOOP task (experiment 1 vs experiment 3).

Figure 2

Predicted and actual performance expectation ratings across time. The behavioral data of the three experiments (averaged across subjects) indicate that participants adapted their performance expectation ratings (solid lines) to the provided feedback, thus learning about their allegedly distinct performance levels in the two ability conditions. In the Agent-LOOP (top and bottom) participants evaluated their own performance more negatively than the other’s performance. Our valence specific learning model captured the participants’ behavior for all experiments. Shaded areas represent the standard errors for the actual performance expectations for each trial. Predicted data (pred.) are represented by the dashed lines.

Figure 3

Structure of the model space for the three experiments. (A) In the Agent-LOOP task (experiments 1 and 3) we distinguished two factors impacting learning rates: the agent (Self vs Other) and the impact (no impact: Unity Model) of the ability condition (Ability Model) or valence (Valence Model). (B) In the Audience-LOOP task the impact of the ability condition or valence on learning rates was assessed within the Private and the Public group separately. For a more detailed description of the model space including initial values for the performance expectations see Supplementary Methods.

Figure 4

Learning rates across the three experiments. The learning rates derived from the Valence Model indicate that there was a bias towards increased updating in response to negative prediction errors (α_PE−) in contrast to positive prediction errors (α_PE+) across all three experiments. This effect was only present when learning about the self (see left and right) and independent of the social context. Bars represent mean learning rates, error bars depict +/− 1 standard error; *indicates a significant interaction effect of PE Valence ^xAgent; ^#indicates a significant main effect of PE Valence across Audience groups.

Figure 5

Correlation plots of self-related Valence Bias Scores and social anxiety as well as self-esteem for the public and private groups. (A) Increased trait self-esteem (SDQ-III score) was associated with a decrease in the negative updating bias about the self in the Public (experiment 3) and the Private group (experiment 1). (B) Trait social anxiety (SIAS score) was associated with increased self-related learning biases towards negative information in the Public groups but not the Private groups (across all experiments).