A pilot study investigating affective forecasting biases with a novel virtual reality-based paradigm

Abstract

A body of research indicates that people are prone to overestimate the affective impact of future events. Here, we developed a novel experimental paradigm to study these affective forecasting biases under laboratory conditions using subjective (arousal and valence) and autonomic measures (skin conductance responses, SCRs, and heart rate). Thirty participants predicted their emotional responses to 15 unpleasant, 15 neutral, and 15 pleasant scenarios (affective forecasting phase) to which they were then exposed in virtual reality (emotional experience phase). Results showed that participants anticipated more extreme arousal and valence scores than they actually experienced for unpleasant and pleasant scenarios. The emotional experience phase was characterized by classic autonomic patterns, i.e., higher SCRs for emotionally arousing scenarios and greater peak cardiac acceleration for pleasant scenarios. During the affective forecasting phase, we found only a moderate association between arousal scores and SCRs and no valence-dependent modulation of cardiac activity. This paradigm opens up new perspectives for investigating affective forecasting abilities under lab-controlled conditions, notably in psychiatric disorders with anxious anticipations.

Figure 1

Illustration of the task. (A) Affective forecasting phase. Each trial started with a fixation cross, followed by the simultaneous display of sentences describing a scenario on a computer screen and through headphones. A second fixation cross was then presented during which participants predicted their emotional responses to the scenario if they were to experience it. Finally, participants completed the valence and arousal scales of the Self-Assessment Manikin (SAM) and rated the frequency of the scenario in daily life on a Likert scale. (B) Emotional experience phase. Each trial started with a fixation cross, followed by the presentation of a scenario on a virtual reality device. Then, participants rated their emotional responses by completing the valence and arousal scales of the SAM.

Figure 2

Subjective and autonomic measures according to Emotion (unpleasant, pleasant, neutral) and Experimental phase (affective forecasting, emotional experience). (A) mean valence score, (B) mean arousal score, (C) mean root-squared ISCR (in microsiemens per second), and (D) mean cardiac acceleration (in beats per minute).

Figure 3

Grand average of heart rate changes (in beats per minute) over time (in seconds), depending on Emotion (unpleasant, pleasant, neutral) and Experimental phase: (A) affective forecasting and (B) emotional experience. The ribbons represent standard error (SE).