State-Aware Deep Item Response Theory using student facial features.

This paper introduces a novel approach to Item Response Theory (IRT) by incorporating deep learning to analyze student facial expressions to enhance the prediction and understanding of student responses to test items. This research is based on the assertion that students' facial expressions offer crucial insights into their cognitive and affective states during testing, subsequently influencing their item responses. The proposed State-Aware Deep Item Response Theory (SAD-IRT) model introduces a new parameter, the student state parameter, which can be viewed as a relative subjective difficulty parameter. It is latent-regressed from students' facial features while solving test items using state-of-the-art deep learning techniques. In an experiment with 20 students, SAD-IRT boosted prediction performance in students' responses compared to prior models without the student state parameter, including standard IRT and its deep neural network implementation, while maintaining consistent predictions of student ability and item difficulty parameters. The research further illustrates the model's early prediction ability in predicting the student's response result before the student answered. This study holds substantial implications for educational assessment, laying the groundwork for more personalized and effective learning and assessment strategies that consider students' emotional and cognitive states.

Interpersonal physiological synchrony is associated with first person and third person subjective assessments of excitement during cooperative joint tasks.

Interpersonal physiological synchrony has been shown to play important roles in social activities. While most studies have shed light on the effects of physiological synchrony on recognition of the group state, such as cohesion or togetherness, the effect of physiological synchrony on the recognition of emotional experience has not been adequately researched. In this study, we examined how physiological synchrony is associated with first- and third-person emotion recognition during a joint task. Two participants played a cooperative block-stacking game (Jenga), alternating their roles as player and adviser, while their heart rates were recorded. The participants evaluated their own emotional experience for each turn. Bystanders watched the game to evaluate the players' emotions. Results showed that the players' subjective excitement increased not only with their own heart rate, but also with increased heart rate synchrony with their adviser. Heart rate synchrony between player and adviser also related to increased intensity in perceived excitement from the bystanders. Given that both first- and third-person emotion recognition can have cumulative impacts on a group, the relationship between physiological synchrony and emotion recognition observed in the present study will help deepen understanding of the psychophysiological mechanisms underlying larger group phenomena such as crowd excitement.

The role of anticipated regret in choosing for others.

In everyday life, people sometimes find themselves making decisions on behalf of others, taking risks on another's behalf, accepting the responsibility for these choices and possibly suffering regret for what they could have done differently. Previous research has extensively studied how people deal with risk when making decisions for others or when being observed by others. Here, we asked whether making decisions for present others is affected by regret avoidance. We studied value-based decision making under uncertainty, manipulating both whether decisions benefited the participant or a partner (beneficiary effect) and whether the partner watched the participant's choices (audience effect) and their factual and counterfactual outcomes. Computational behavioural analysis revealed that participants were less mindful of regret (and more strongly driven by bigger risks) when choosing for others vs for themselves. Conversely, they chose more conservatively (regarding both regret and risk) when being watched vs alone. The effects of beneficiary and audience on anticipated regret counteracted each other, suggesting that participants' financial and reputational interests impacted the feeling of regret independently.

Parsing cultural impacts on regret and risk in Iran, China and the United Kingdom.

Value-based choices are influenced both by powerful counterfactuals, such as regret, and also by risk in potential outcomes. Culture can profoundly affect how humans perceive and act in the world, but it remains unknown how regret in value-based choice and key aspects of risk-taking may differ between cultures. Here our computational approach provides precise and independent metrics, grounded in extensive neurobiological evidence, for the influences of risk and regret on choice. We test for commonalities and differences across three diverse cultures: Iran, China and the UK. Including Iran matters because cross-cultural work on value-based choice is lacking for this key 21st Century culture, and also because patterns across the three cultures arbitrates between explanations for differences. We find commonalities, with regret influencing choice across cultures and no consistent cultural difference seen. However, for risk, unlike in both Chinese and Westerners' choices, Iranians are risk-seeking - findings consistent across two task variants and further explained by Iranians showing less subjective impact of negative, but not positive, outcomes of risky choices. Our computational approach dissects cultural impacts on two key neurobiologically-grounded quantities in value-based choice, showing that neuroscientific accounts cannot a priori isolate such quantities from culture in the cognitive processes underlying choice.