skip to main content


Title: When Shall I Be Empathetic? The Utility of Empathetic Parameter Estimation in Multi-Agent Interactions
Award ID(s):
1925403
NSF-PAR ID:
10352986
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
2021 IEEE International Conference on Robotics and Automation (ICRA)
Page Range / eLocation ID:
2761 to 2767
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Daher-Nashif, Suhad (Ed.)

    Empathy is at the core of our social world, yet multidomain factors that affect its development in socially sensitive periods, such as adolescence, are incompletely understood. To address this gap, this study investigated associations between social, environmental and mental health factors, and their temporal changes, on adolescent empathetic behaviors/emotions and, for comparison, callous unemotional (CU) traits and behaviors, in the early longitudinal Adolescent Brain Cognitive Development sample (baseline: n = 11062; 2-year follow-up: n = 9832, median age = 119 and 144 months, respectively). Caregiver affection towards the youth, liking school, having a close friend, and importance of religious beliefs/spirituality in the youth’s life were consistently positively correlated with empathetic behaviors/emotions across assessments (p<0.001, Cohen’s f = ~0.10). Positive family dynamics and cohesion, living in a neighborhood that shared the family’s values, but also parent history of substance use and (aggregated) internalizing problems were additionally positively associated with one or more empathetic behaviors at follow-up (p<0.001, f = ~0.10). In contrast, externalizing problems, anxiety, depression, fear of social situations, and being withdrawn were negatively associated with empathetic behaviors and positively associated with CU traits and behaviors (p<0.001, f = ~0.1–0.44). The latter were also correlated with being cyberbullied and/or discriminated against, anhedonia, and impulsivity, and their interactions with externalizing and internalizing issues. Significant positive temporal correlations of behaviors at the two assessments indicated positive (early) developmental empathetic behavior trajectories, and negative CU traits’ trajectories. Negative changes in mental health adversely moderated positive trajectories and facilitated negative ones. These findings highlight that adolescent empathetic behaviors/emotions are positively related to multidomain protective social environmental factors, but simultaneously adversely associated with risk factors in the same domains, as well as bully victimization, discrimination, and mental health problems. Risk factors instead facilitate the development of CU traits and behaviors.

     
    more » « less
  2. Abstract

    People may experience emotions before interacting with automated agents to seek information and support. However, existing literature has not well examined how human emotional states affect their interaction experience with agents or how automated agents should react to emotions. This study proposes to test how participants perceive an empathetic agent (chatbot) vs. a non-empathetic one under various emotional states (i.e., positive, neutral, negative) when the chatbot mediates the initial screening process for student advising. Participants are prompted to recall a previous emotional experience and have text-based conversations with the chatbot. The study confirms the importance of presenting empathetic cues in the design of automated agents to support human-agent collaboration. Participants who recall a positive experience are more sensitive to the chatbot’s empathetic behavior. The empathetic behavior of the chatbot improves participants’ satisfaction and makes those who recall a neutral experience feel more positive during the interaction. The results reveal that participants’ emotional states are likely to influence their tendency to self-disclose, interaction experience, and perception of the chatbot’s empathetic behavior. The study also highlights the increasing need for emotional acknowledgment of people who experience positive emotions so that design efforts need to be designated according to people’s dynamic emotional states.

     
    more » « less
  3. null (Ed.)
  4. Natural Human-Robot interaction (HRI) attracts considerable interest in letting robots understand the users’ emotional state. This paper demonstrates a method to introduce the affection model to the robotic system’s conversational agent to provide natural and empathetic HRI. We use a large-scale pre-trained language model and fine-tune it on a dialogue dataset with empathetic characteristics. Based on existing studies’ progress, we extend the current method and enable the agent to perform advanced sentiment analysis using the affection model. This dialogue agent will allow the robot to provide natural response along with emotion classification and the estimations of arousal and valence level. We evaluate our model using different metrics, comparing it with the recent studies and showing its emotion detection capacity. 
    more » « less