“Elinor’s Talking to Me!”:Integrating Conversational AI into Children’s Narrative Science Programming

Xu, Ying; Vigil, Valery; Bustamante, Andres S.; Warschauer, Mark

doi:10.1145/3491102.3502050

Cited by 15 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a substantial body of prior studies showing that children can learn from their interactions with AI. However, these learning experiences were primarily structured to align with formal pedagogical discourse, in which children were expected to respond to the AI's questions with definitive, correct answers [100,102,103]. However, our study goes further to suggest that children can acquire mathematical language through free-form interactions in a narrative-based context with AI, replicating the benefits of the approach used by human educators to teach mathematical language through storytelling.…”

Section: Ai As Storytelling and Learning Partnersmentioning

confidence: 75%

“…In particular, the study highlighted the facilitator's role in posing questions to guide children's responses and offer constructive feedback responsive to children's contributions. Such question-feedback-scaffolding could potentially lower the cognitive demand required for certain challenges children face when continuing the story [102]. Building on this concept, the HCI community has long been exploring technology-mediated platforms to support children storytelling.…”

Section: Teaching Math Language Through Storytellingmentioning

confidence: 99%

“…Previous research has identified two prevalent types of interactions that children tend to have with CUIs [101]: voice assistants supporting open-domain conversations (e.g., Apple Siri, Amazon Alexa, Google Assistant) and voice-based apps that specifically designed for children for domain-specific conversations [8,9,56,62,63]. This type of specifically design apps have been found to support children's learning across a number of disciplines, including math [40,98], science [102], computational thinking [18], and literacy [101]. Though varied in their specific design, these applications are grounded in a common principle by utilizing conversational AI as a language partner to engage children in discussions related to the relevant topics.…”

Section: Conversational Interfaces For Childrenmentioning

confidence: 99%

“…How many steps do you think they should both count?"). This strategy, simplifying the original open-ended question by suggesting a specific direction, is widely utilized in conversational agents to engage preschool-aged children [33,34,102].…”

Section: Design Principlesmentioning

confidence: 99%

“…If Lucy takes 5 steps, then Nick also takes 5 steps." These types of explanations, integrated within the context, are deemed more effective for young children than abstract definitions [18,32,102].…”

Section: Design Principlesmentioning

confidence: 99%

See 4 more Smart Citations

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Zhang,

Liu,

Ziska

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

Figure 1: Interaction between a child and Mathemyths: demonstrating the system's ability to teach mathematical language through child-AI co-creative storytelling. Mathemyths provides open-ended questions to solicit how the child wishes the story should progress, on-the-fly feedback to acknowledge the child's responses, and co-creative story continuation with in-context explanations of math words. When the child needs additional support to continue the story, Mathemyths offers scaffolding through follow-up questions and "hint & rephrase" strategies.

show abstract

Section: Ai As Storytelling and Learning Partnersmentioning

confidence: 75%

Section: Teaching Math Language Through Storytellingmentioning

confidence: 99%

Section: Conversational Interfaces For Childrenmentioning

confidence: 99%

Section: Design Principlesmentioning

confidence: 99%

Section: Design Principlesmentioning

confidence: 99%

See 3 more Smart Citations

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Zhang,

Liu,

Ziska

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

Intrinsic Motivation for Social Media Literacy, a Look into the Narrative Scripts

Lobo-Quintero

Reina

Theophilou

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

Social media embodies the idyllic representation of the information society providing users opportunities to connect and communicate. Likewise, it can represent humanity’s worst nightmare with a plethora of negative phenomena. Different forms of media literacy interventions have been designed as preventative tools to counteract the negative phenomena of social media. One such approach, the narrative scripts, sees the integration of a social media intervention within a controlled social media platform. With an importance to design engaging educational tools to get learners attention without limiting the educational deliverables, the narrative scripts approach sees the implementation of gamifying elements to help deliver the learning material and motivate learners to participate. To assess the effectiveness of the proposed motivational properties of the narrative scripts, a descriptive exploratory study was designed. In total 124 adolescents participated in a social media literacy workshop powered by the narrative scripts. During the workshop students completed missions assigned by a virtual learning companion and participated in collaborative learning activities. To measure the motivation levels of the students, the Intrinsic Motivation Inventory was applied. Results demonstrate that adolescents found the narrative scripts an interesting and enjoyable activity. Qualitative analysis supported the findings with adolescents describing the activities as dynamic and entertaining. The results from this study provide insights towards the motivational aspects of the narrative scripts as a social media intervention tool.

show abstract

Influencing human–AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness

Pataranutaporn,

Liu,

Finn

et al. 2023

Nat Mach Intell

View full text Add to dashboard Cite

“Elinor’s Talking to Me!”:Integrating Conversational AI into Children’s Narrative Science Programming

Cited by 15 publications

References 59 publications

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling

Intrinsic Motivation for Social Media Literacy, a Look into the Narrative Scripts

Influencing human–AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness

Contact Info

Product

Resources

About