Affective computing research has advanced emotion recognition systems using facial expressions, voices, gaits, and physiological signals, yet these methods are often impractical. This study integrates mouse cursor motion analysis into affective computing and investigates the idea that movements of the computer cursor can provide information about emotion of the computer user. We extracted 16–26 trajectory features during a choice-reaching task and examined the link between emotion and cursor motions. Participants were induced for positive or negative emotions by music, film clips, (...) or emotional pictures, and they indicated their emotions with questionnaires. Our 10-fold cross-validation analysis shows that statistical models formed from “known” participants could predict nearly 10%–20% of the variance of positive affect and attentiveness ratings of “unknown” participants, suggesting that cursor movement patterns such as the area under curve and direction change help infer emotions of computer users. (shrink)

Recent research has documented that affect plays a crucial role in risk perception. When no information about numerical risk estimates is available (e.g., probability of loss or magnitude of consequences), people may rely on positive and negative affect toward perceived risk. However, determinants of affective reactions to risks are poorly understood. In a series of three experiments, we addressed the question of whether and to what degree mental imagery eliciting negative affect and stress influences risk perception. In each experiment, participants (...) were instructed to visualize consequences of risk taking and to rate riskiness. In Experiment 1, participants who imagined negative risk consequences reported more negative affect and perceived risk as higher compared to the control condition. In Experiment 2, we found that this effect was driven by affect elicited by mental imagery rather than its vividness and intensity. In this study, imagining positive risk consequences led to lower perceived risk than visualizing negative risk consequences. Finally, we tested the hypothesis that negative affect related to higher perceived risk was caused by negative feelings of stress. In Experiment 3, we introduced risk-irrelevant stress to show that participants in the stress condition rated perceived risk as higher in comparison to the control condition. This experiment showed that higher ratings of perceived risk were influenced by psychological stress. Taken together, our results demonstrate that affect-laden mental imagery dramatically changes risk perception through negative affect (i.e., psychological stress). (shrink)