When Does Oxytocin Affect Human Memory Encoding? The Role of Social Context and Individual Attachment Style

Abstract

The neuropeptide oxytocin plays an essential role in regulating social behavior and has been implicated in a variety of human cognitive processes in the social domain, including memory processes. The present study investigates the influence of oxytocin on human memory encoding, taking into account social context and personality, which have previously been neglected as moderators for how oxytocin affects memory encoding. To examine the role of social context of encoding, we employed an established experimental paradigm in which participants perform a word-categorization task in either a joint (social) or individual (non-social) setting. To investigate the role of socially relevant personality factors, participants' adult attachment style (AAS) was assessed. Previous research has identified attachment style as a potent moderator of oxytocin effects in the social-cognitive domain, but here we investigated for the first time its role in memory encoding. Participants were invited in pairs and received either placebo or oxytocin intranasally. Forty-five minutes later, they were instructed to react to different word categories within a list of successively presented words. This task was performed individually in the non-social condition and simultaneously with the partner in the social condition. After a 24-h delay, memory for all words was tested individually in a surprise recognition memory test. Oxytocin effects on memory accuracy depended on participants' AAS. Specifically, oxytocin positively affected memory for participants who scored low on attachment dependence (who find dependence on others uncomfortable), but negatively affected memory for high scorers (who are comfortable depending on others). Oxytocin effects were not moderated by social vs. non-social context at encoding, and we discuss reasons for this outcome. Regardless of encoding condition or personality, oxytocin led to more liberal responding in the recognition memory test, which was also reflected in significantly higher false alarm rates (FARs) and a trend towards higher hit rates (HRs) compared to placebo. Overall, our results are consistent with an interactionist view on oxytocin effects on human cognitive functioning. Future research should further examine how oxytocin affects response biases via previous encoding and the ways in which biological dispositions linked to attachment style affect the process of memory encoding.

Keywords: adult attachment style; joint action task; memory encoding; oxytocin; social context.

Figure 1

Social context manipulation at encoding. Participants always had the task to press a key whenever a word of a specific semantic category (e.g., animals) appeared on the screen. They performed the word categorization task once individually (non-social context, left) and once jointly with another participant (social context, right) who at the same time had the task to press a key in response to a different semantic category (e.g., household objects). The order of social and non-social context conditions was balanced across subjects. Participant were told that during individual task performance, the other participant would perform an unrelated other task in the adjacent room. This example illustrates the non-social and social context condition for the person on the left who has the task to respond to the word category “animals”. The black arrow indicates that this person has to press the key for the currently presented word.

Figure 2

Main effects of oxytocin vs. placebo treatment on different recognition memory parameters. Compared to placebo, oxytocin led to more liberal responding at memory testing (increase in the response bias parameter B_r), as reflected also in a higher false alarm rate (FAR) and, as a trend, a higher hit rate (HR). In contrast, there was no overall effect of oxytocin on actual bias-corrected memory accuracy (P_r). *p < 0.05, ^#p < 0.10.

Figure 3

Oxytocin effects on actual memory accuracy (P_r), depending on adult attachment style (AAS) Dependence. A crossover interaction shows that oxytocin had opposite effects on memory encoding for low and high scorers. Data points selected for illustration refer to 1 standard deviation below and 1 standard deviation above the sample mean.