Towards Automatic Generation of Peer-Targeted Science Talk in Curiosity-Evoking Virtual Agent

Paranjape, Bhargavi; Ge, Yubin; Bai, Zhen; Hammer, Jessica; Cassell, Justine

doi:10.1145/3267851.3267894

Cited by 8 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An ideal way to build a dataset for conversational agents is to record conversations from children's real-life social interactions (e.g., Paranjape et al, 2018 ). As mentioned previously, creating a new database provides control over what the agent learns and increases flexibility to mold the dataset to create a child-centric agent.…”

Section: Generating Data For Children's Conversational Agentsmentioning

confidence: 99%

“…To collect data, at least two children must be brought together to talk in a naturalistic setting where they can interact with one another, such as playing games or learning a lesson (Paranjape et al, 2018 ). The aim is not to control children's interactions but to facilitate sessions in which they can talk and socially engage with one another.…”

Section: Generating Data For Children's Conversational Agentsmentioning

confidence: 99%

See 1 more Smart Citation

A Perspective on Building Ethical Datasets for Children's Conversational Agents

Bailey

Patel

Gurari

2021

Front. Artif. Intell.

View full text Add to dashboard Cite

Artificial intelligence (AI)-powered technologies are becoming an integral part of youth's environments, impacting how they socialize and learn. Children (12 years of age and younger) often interact with AI through conversational agents (e.g., Siri and Alexa) that they speak with to receive information about the world. Conversational agents can mimic human social interactions, and it is important to develop socially intelligent agents appropriate for younger populations. Yet it is often unclear what data are curated to power many of these systems. This article applies a sociocultural developmental approach to examine child-centric intelligent conversational agents, including an overview of how children's development influences their social learning in the world and how that relates to AI. Examples are presented that reflect potential data types available for training AI models to generate children's conversational agents' speech. The ethical implications for building different datasets and training models using them are discussed as well as future directions for the use of social AI-driven technology for children.

show abstract

Section: Generating Data For Children's Conversational Agentsmentioning

confidence: 99%

Section: Generating Data For Children's Conversational Agentsmentioning

confidence: 99%

A Perspective on Building Ethical Datasets for Children's Conversational Agents

Bailey

Patel

Gurari

2021

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…The architecture underlying the virtual peer resembles a dialogue system architecture. The first module developed has been a verbal behavior generation module [86] that allows the virtual peer to produce age-appropriate curiosity-inducing conversational moves including question asking, hypothesis verbalization, argument, and justification during the discussions elicited by the collaborative board game. This generation module allows the virtual peer to generate the kind of sentences that the human-human analyses described above have shown to increase curiosity.…”

Section: Implementation In Pedagogical Agentsmentioning

confidence: 99%

A Novel Multimodal Approach for Studying the Dynamics of Curiosity in Small Group Learning

Sinha¹,

Zhang²,

Cassell³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Curiosity is a vital metacognitive skill in educational contexts, leading to creativity, and a love of learning. And while many school systems increasingly undercut curiosity by teaching to the test, teachers are increasingly interested in how to evoke curiosity in their students to prepare them for a world in which lifelong learning and reskilling will be more and more important. One aspect of curiosity that has received little attention, however, is the role of peers in eliciting curiosity. We present what we believe to be the first theoretical framework that articulates an integrated socio-cognitive account of curiosity that ties observable behaviors in peers to underlying curiosity states. We make a bipartite distinction between individual and interpersonal functions that contribute to curiosity, and multimodal behaviors that fulfill these functions. We validate the proposed framework by leveraging a longitudinal latent variable modeling approach. Findings confirm a positive predictive relationship between the latent variables of individual and interpersonal functions and curiosity, with the interpersonal functions exercising a comparatively stronger influence. Prominent behavioral realizations of these functions are also discovered in a data-driven manner. We instantiate the proposed theoretical framework in a set of strategies and tactics that can be incorporated into learning technologies to indicate, evoke, and scaffold curiosity. This work is a step towards designing learning technologies that can recognize and evoke moment-by-moment curiosity during learning in social contexts and towards a more complete multimodal learning analytics. The underlying rationale is applicable more generally for developing computer support for other metacognitive and socio-emotional skills.

show abstract

The impact of near-peer virtual agents on computer science attitudes and collaborative dialogue

Earle-Randell,

Wiggins,

et al. 2024

International Journal of Child-Computer Interaction

View full text Add to dashboard Cite

Towards Automatic Generation of Peer-Targeted Science Talk in Curiosity-Evoking Virtual Agent

Cited by 8 publications

References 32 publications

A Perspective on Building Ethical Datasets for Children's Conversational Agents

A Perspective on Building Ethical Datasets for Children's Conversational Agents

A Novel Multimodal Approach for Studying the Dynamics of Curiosity in Small Group Learning

The impact of near-peer virtual agents on computer science attitudes and collaborative dialogue

Contact Info

Product

Resources

About