Education and AI B

会議の名前
CHI 2024
Scientific and Fantastical: Creating Immersive, Culturally Relevant Learning Experiences with Augmented Reality and Large Language Models
要旨

Motivating children to learn is a major challenge in education. One way to inspire motivation to learn is through immersion. We combine the immersive potential of augmented reality (AR), narrative, and large language models (LLMs) to bridge fantasy with reality in a mobile application, Moon Story, that teaches elementary schoolers astronomy and environmental science. Our system also builds upon learning theories such as culturally-relevant pedagogy. Using our application, a child embarks on a journey inspired by Chinese mythology, engages in real-world AR activities, and converses with a fictional character powered by a LLM. We conducted a controlled experiment (N=50) with two conditions: one using an LLM and one that was hard-coded. Both conditions resulted in learning gains, high engagement levels, and increased science learning motivation. Participants in the LLM condition also wrote more relevant answers. Finally, participants of both Chinese and non-Chinese heritage found the culturally-based narrative compelling.

著者
Alan Y.. Cheng
Stanford University, Stanford, California, United States
Meng Guo
Stanford University, Stanford, California, United States
Melissa Ran
Stanford University, Stanford, California, United States
Arpit Ranasaria
Stanford University, Stanford, California, United States
Arjun Sharma
Stanford University, Stanford, California, United States
Anthony Xie
Stanford University, Stanford, California, United States
Khuyen N.. Le
University of California, San Diego, La Jolla, California, United States
Bala Vinaithirthan
Stanford University, Stanford, California, United States
Shihe (Tracy) Luan
Stanford University, Stanford, California, United States
David Thomas Henry. Wright
Nagoya University, Nagoya, Aichi, Japan
Andrea Cuadra
Stanford University, Stanford, California, United States
Roy Pea
Stanford University, Stanford, California, United States
James A.. Landay
Stanford University, Stanford, California, United States
論文URL

https://doi.org/10.1145/3613904.3642041

動画
VIVID: Human-AI Collaborative Authoring of Vicarious Dialogues from Lecture Videos
要旨

The lengthy monologue-style online lectures cause learners to lose engagement easily. Designing lectures in a “vicarious dialogue” format can foster learners’ cognitive activities more than monologue-style. However, designing online lectures in a dialogue style catered to the diverse needs of learners is laborious for instructors. We conducted a design workshop with eight educational experts and seven instructors to present key guidelines and the potential use of large language models (LLM) to transform a monologue lecture script into pedagogically meaningful dialogue. Applying these design guidelines, we created VIVID which allows instructors to collaborate with LLMs to design, evaluate, and modify pedagogical dialogues. In a within-subjects study with instructors (N=12), we show that VIVID helped instructors select and revise dialogues efficiently, thereby supporting the authoring of quality dialogues. Our findings demonstrate the potential of LLMs to assist instructors with creating high-quality educational dialogues across various learning stages.

著者
Seulgi Choi
KAIST, Daejeon, Korea, Republic of
Hyewon Lee
KAIST, Daejeon, Korea, Republic of
Yoonjoo Lee
KAIST, Daejeon, Korea, Republic of
Juho Kim
KAIST, Daejeon, Korea, Republic of
論文URL

https://doi.org/10.1145/3613904.3642867

動画
Exploring AI Problem Formulation with Children via Teachable Machines
要旨

Emphasizing problem formulation in AI literacy activities with children is vital, yet we lack empirical studies on their structure and affordances. We propose that participatory design involving teachable machines facilitates problem formulation activities. To test this, we integrated problem reduction heuristics into storyboarding and invited a university-based intergenerational design team of 10 children (ages 8-13) and 9 adults to co-design a teachable machine. We find that children draw from personal experiences when formulating AI problems; they assume voice and video capabilities, explore diverse machine learning approaches, and plan for error handling. Their ideas promote human involvement in AI, though some are drawn to more autonomous systems. Their designs prioritize values like capability, logic, helpfulness, responsibility, and obedience, and a preference for a comfortable life, family security, inner harmony, and excitement as end-states. We conclude by discussing how these results can inform the design of future participatory AI activities.

受賞
Honorable Mention
著者
Utkarsh Dwivedi
University of Maryland, College Park, Maryland, United States
Salma Elsayed-Ali
University of Maryland, College Park, Maryland, United States
Elizabeth Bonsignore
University of Maryland, College Park, Maryland, United States
Hernisa Kacorri
University of Maryland, College Park, Maryland, United States
論文URL

https://doi.org/10.1145/3613904.3642692

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

Mathematical language is a cornerstone of a child's mathematical development, and children can effectively acquire this language through storytelling with a knowledgeable and engaging partner. In this study, we leverage the recent advances in large language models to conduct free-form, creative conversations with children. Consequently, we developed Mathemyths, a joint storytelling agent that takes turns co-creating stories with children while integrating mathematical terms into the evolving narrative. This paper details our development process, illustrating how prompt-engineering can optimize LLMs for educational contexts. Through a user study involving 35 children aged 4-8 years, our results suggest that when children interacted with Mathemyths, their learning of mathematical language was comparable to those who co-created stories with a human partner. However, we observed differences in how children engaged with co-creation partners of different natures. Overall, we believe that LLM applications, like Mathemyths, offer children a unique conversational experience pertaining to focused learning objectives.

著者
Chao Zhang
Cornell University, Ithaca, New York, United States
Xuechen Liu
University of Michigan, Ann Arbor, Michigan, United States
Katherine Ziska
University of Michigan, Ann Arbor, Michigan, United States
Soobin Jeon
University of Michigan, Ann Arbor, Michigan, United States
Chi-Lin Yu
University of Michigan, Ann Arbor, Michigan, United States
Ying Xu
University of Michigan, Ann Arbor, Michigan, United States
論文URL

https://doi.org/10.1145/3613904.3642647

動画
Testing, Socializing, Exploring: Characterizing Middle Schoolers’ Approaches to and Conceptions of ChatGPT
要旨

As generative AI rapidly enters everyday life, educational interventions for teaching about AI need to cater to how young people, in particular middle schoolers who are at a critical age for reasoning skills and identity formation, conceptualize and interact with AI. We conducted nine focus groups with 24 middle school students to elicit their interests, conceptions of, and approaches to a popular generative AI tool, ChatGPT. We highlight a) personally and culturally-relevant topics to this population, b) three distinct approaches in students' open-ended interactions with ChatGPT: AI testing-oriented, AI socializing-oriented, and content exploring-oriented, and 3) an improved understanding of youths' conceptions and misconceptions of generative AI. While misconceptions highlight gaps in understanding what generative AI is and how it works, most learners show interest in learning about what AI is and what it can do. We discuss the implications of these conceptions for designing AI literacy interventions in museums.

著者
Yasmine Belghith
Georgia Institute of Technology, Atlanta, Georgia, United States
Atefeh Mahdavi Goloujeh
Georgia Institute of Technology, Atlanta, Georgia, United States
Brian Magerko
Georgia Tech, Atlanta, Georgia, United States
Duri Long
Northwestern University, Evanston, Illinois, United States
Tom McKlin
125 E. Trinity Place, Ste 249, Decatur, Georgia, United States
Jessica Roberts
Georgia Institute of Technology, Atlanta, Georgia, United States
論文URL

https://doi.org/10.1145/3613904.3642332

動画