An official website of the United States government
Conversational AIs such as Alexa and ChatGPT are increasingly ubiquitous in young people’s lives, but these young users are often not afforded the opportunity to learn about the inner workings of these technologies. One of the most powerful ways to foster this learning is to empower youth to create AI that is personally and socially meaningful to them. We have built a novel development environment, AMBY–‘‘AI Made By You’’–for youth to create conversational agents. AMBY was iteratively designed with and for youth aged 12–13 through contextual inquiry and usability studies. AMBY is designed to foster AI learning with features that enable users to generate training datasets and visualize conversational flow. We report on results from a two-week summer camp deployment, and contribute design implications for conversational AI authoring tools that empower AI learning for youth.
more »
« less
Temporal asymmetries in inferring unobserved past and future events
Abstract Unlike temporally symmetric inferences about simple sequences, inferences about our own lives are asymmetric: we are better able to infer the past than the future, since we remember our past but not our future. Here we explore whether there are asymmetries in inferences about the unobserved pasts and futures of other people’s lives. In two experiments (analyses of the replication experiment were pre-registered), our participants view segments of two character-driven television dramas and write out what they think happens just before or after each just-watched segment. Participants are better at inferring unseen past (versus future) events. This asymmetry is driven by participants’ reliance on characters’ conversational references in the narrative, which tend to favor the past. This tendency is also replicated in a large-scale analysis of conversational references in natural conversations. Our work reveals a temporal asymmetry in how observations of other people’s behaviors can inform inferences about the past and future.
more »
« less
- Award ID(s):
- 2145172
- PAR ID:
- 10546119
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Nature Communications
- Volume:
- 15
- Issue:
- 1
- ISSN:
- 2041-1723
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We study two approaches for predicting an appropriate pose for a robot to take part in group formations typical of social human conversations subject to the physical layout of the surrounding environment. One method is model-based and explicitly encodes key geometric aspects of conversational formations. The other method is data-driven. It implicitly models key properties of spatial arrangements using graph neural networks and an adversarial training regimen. We evaluate the proposed approaches through quantitative metrics designed for this problem domain and via a human experiment. Our results suggest that the proposed methods are effective at reasoning about the environment layout and conversational group formations. They can also be used repeatedly to simulate conversational spatial arrangements despite being designed to output a single pose at a time. However, the methods showed different strengths. For example, the geometric approach was more successful at avoiding poses generated in nonfree areas of the environment, but the data-driven method was better at capturing the variability of conversational spatial formations. We discuss ways to address open challenges for the pose generation problem and other interesting avenues for future work.more » « less
-
Abstract How do we learn who is good at what? Building on the idea that humans draw rich inferences from others’ emotional expressions, here we ask whether others’ surprised reactions to performance outcomes can elicit inferences about competence. Across three experiments, participants were asked to choose “who is better” in scenarios where two students performed identically on the same task but their teacher expressed surprise to only one of them. In Experiment 1 (n = 60, adults) and Experiment 2 (n = 90, 6- to 8-year-old children), participants’ responses were modulated by not only the students’ performance outcomes (success or failure) but also the teacher’s response to the outcomes (surprise or no surprise). Specifically, participants preferentially chose the student who did not elicit the teacher’s surprise as more competent when both students succeeded, but chose the student who elicited surprise when both failed. Experiment 3a (n = 150, 4- to 8-year-olds) replicated this pattern in 6- to 8-year-olds as a group—but not in 4- to 5-year-olds—with increasing robustness with age. Finally, this pattern was significantly reduced in Experiment 3b where the teacher’s surprise was directed at an irrelevant event rather than the student’s performance (n = 90, 6- to 8-year-olds). Taken together, these results suggest that even non-valenced emotional reactions to performance outcomes—being surprised at someone’s success or failure—can inform inferences about valenced qualities such as competence. More broadly, the current findings demonstrate that emotional expressions we observe in our daily lives can lead to nuanced yet consequential social judgments.more » « less
-
As the influence of social robots in people’s daily lives grows, research on understanding people’s perception of robots including sociability, trust, acceptance, and preference becomes more pervasive. Research has considered visual, vocal, or tactile cues to express robots’ emotions, whereas little research has provided a holistic view in examining the interactions among different factors influencing emotion perception. We investigated multiple facets of user perception on robots during a conversational task by varying the robots’ voice types, appearances, and emotions. In our experiment, 20 participants interacted with two robots having four different voice types. While participants were reading fairy tales to the robot, the robot gave vocal feedback with seven emotions and the participants evaluated the robot’s profiles through post surveys. The results indicate that (1) the accuracy of emotion perception differed depending on presented emotions, (2) a regular human voice showed higher user preferences and naturalness, (3) but a characterized voice was more appropriate for expressing emotions with significantly higher accuracy in emotion perception, and (4) participants showed significantly higher emotion recognition accuracy with the animal robot than the humanoid robot. A follow-up study ([Formula: see text]) with voice-only conditions confirmed that the importance of embodiment. The results from this study could provide the guidelines needed to design social robots that consider emotional aspects in conversations between robots and users.more » « less
-
Abstract People’s beliefs are influenced by interactions within their communities. The propagation of this influence through conversational social networks should impact the degree to which community members synchronize their beliefs. To investigate, we recruited a sample of 140 participants and constructed fourteen 10-member communities. Participants first rated the accuracy of a set of statements (pre-test) and were then provided with relevant evidence about them. Then, participants discussed the statements in a series of conversational interactions, following pre-determined network structures (clustered/non-clustered). Finally, they rated the accuracy of the statements again (post-test). The results show that belief synchronization, measuring the increase in belief similarity among individuals within a community from pre-test to post-test, is influenced by the community’s conversational network structure. This synchronization is circumscribed by a degree of separation effect and is equivalent in the clustered and non-clustered networks. We also find that conversational content predicts belief change from pre-test to post-test.more » « less
