Explore with Me: Peer Observation Decreases Risk-Taking but Increases Exploration Tendencies across Adolescence

Abstract

It has been assumed that adolescents increase risk-taking tendencies when peers are present but findings on experimental decision-making have been inconclusive. Most studies focus on risk-taking tendencies, ignoring the effects peer presence can exert over other cognitive processes involved in decision-making, as well as any other underlying developmental and individual differences. In the present study, the trial-by-trial choice behavior was analyzed in a task in which adolescents adjust to dynamically changing risk probabilities. Using Bayesian modeling, the study aimed to infer about peer presence effects on risk-taking tendencies but also on reactions to, exploration of, and learning from positive and negative outcomes of risk-taking. 184 pre- to late adolescents (M = 14.09 years, min = 8.59, max = 18.97, SD = 2.95, 47% female) conducted the Balloon Analog Risk Task under two conditions: Once alone and once in the presence of a (non-existent) peer observing them virtually. Findings revealed that (a) peer observation reduced risk-taking but increased exploration tendencies and (b) that individual differences modulated this effect. Especially female pre-adolescents increased their openness to explore different choice outcomes when a peer observed their behavior. These results support the assumption that the occurrence and direction of peer influences on risk-taking depend on a person-environment interaction, emphasizing the dynamic role peers play in adolescent risk-taking.

Keywords: Adolescence; Computational modeling; Decision-making; Exploration; Individual differences; Peer presence.

Fig. 1

Illustration of the BART environment. Participants were instructed to gain as much money as possible by inflating balloons. Each balloon was treated as a trial and the number of balloons left was visible in the middle of the upper part of the screen. At any time, participants had to decide to either pump a balloon by pressing the button in the middle of the screen (space key) or to save the amount gained with previous pumps (down arrow key) and begin with a new balloon. The virtual account and amount of money earned with the previous balloon were visible on the upper right of the screen. Each pump increased the outcome of a balloon by 5 cents. However, participants were informed that the balloon could burst at a random inflation point and that all temporary gains would be lost if not saved to the virtual account. No further information, i.e., about burst probabilities, was given

Fig. 2

Illustration of the Chat environment as seen by a female participant. Participants were informed about a peer who would observe them via webcam during the conduction of the Balloon Analog Risk Task (BART). Before the peer observation condition block, they were introduced to the peer via a chat environment. Participants provided information about their name, age, grade, and hobbies in an otherwise preformulated chat message. Unbeknownst to the participants, the peers' answer that appeared after a short period was a randomly generated text message that matched the participants' information about gender and grade, as well as age by plus/minus one year

Fig. 3. Predicted results of general linear mixed effects regression (glmer) on the number of pumps for the peer observation conditions across age and trials.

A Age trends (age range = 9–19 years, mean age = 14 years) in the predicted number of pumps as a function of Trial Number (range 2–30; normalized for each condition) for the two peer observation conditions (absent/present; −1/1). B Age trends (range = 9–19 years, M = 14 years) in the predicted number of pumps as a function of the peer observation conditions (absent/present; −1/1) for early and late trials (Trial Number; range 2–30; normalized for each condition). The predicted values and error bands (standard errors) are from the final model with continuous age in its original scale. The effects plots are averaged across Previous Outcome, RPI, and Gender

Fig. 4. Predicted results of linear mixed effects regression (lmer) on exploration tendencies for the peer observation conditions and genders across age.

A Moderation of gender (female/male; −1/1) on age trends (age range = 9–19 years, mean age = 14 years) in the effect of peer observation conditions (absent/present; −1/1) on exploration tendencies during the Balloon Analog Risk Task (BART). B Moderation of peer observation condition (absent/present; −1/1) on differences in age trends (age range = 9–19 years, mean age = 14 years) between the genders (female/male; −1/1) in exploration tendencies during the Balloon Analog Risk Task (BART). The predicted values and error bands (standard errors) are from the final model with continuous age in its original scale. Predicted values are averaged across RPI scores and the y-axis was inverted to reflect exploration tendencies

Fig. 5

The effect of peer observation condition (absent/present; −1/1) in the predicted number of pumps of the Balloon Analog Risk Task (BART) as a function of resistance to peer influence (RPI) scores (standardized). The predicted values and error bands (standard errors) are averaged across Age, Trial Number, Previous Outcome, and Gender