Zhenyao Cai

Zhenyao Cai

Auto-generated profile, based on publicly available information

Zhenyao Cai

School of Education, University of California Irvine, Irvine, California, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 June 2023
Verified
Conference Paper
Open access
AHAriel Han
Ariel Han
ZCZhenyao Cai
Zhenyao Cai
The study examines the design implications of leveraging generative AI tools such as ChatGPT, Stable Diffusion, Midjourney for literacy development and creative expression for children [6, 8, 18]. We sought to elicit insights on the applicability of generative AI for educational purposes from various stakeholders (i.e., parents, teachers, and AI researchers). We recruited nine participants to elicit their perspectives on designing a visual narrative app with generative AI. We examined the opportunities and limitations of the current generative AI tools. Using the implications from our evaluation, we propose AIStory, an AI-powered visual storytelling application prototype that can be used for children’s creative expression, storytelling, and literacy development.

11 May 2024
Verified
Conference Paper
Open access
AHAriel Han
Ariel Han
XZXiaofei Zhou
Xiaofei Zhou
ZCZhenyao Cai
Zhenyao Cai
SHShenshen Han
Shenshen Han
RKRichard Ko
Richard Ko
Kylie PepplerKylie Peppler
Kylie Peppler
The viral launch of new generative AI (GAI) systems, such as ChatGPT and Text-to-Image (TTL) generators, sparked questions about how they can be effectively incorporated into writing education. However, it is still unclear how teachers, parents, and students perceive and suspect GAI systems in elementary school settings. We conducted a workshop with twelve families (parent-child dyads) with children ages 8-12 and interviewed sixteen teachers in order to understand each stakeholder’s perspectives and opinions on GAI systems for learning and teaching writing. We found that the GAI systems could be beneficial in generating adaptable teaching materials for teachers, enhancing ideation, and providing students with personalized, timely feedback. However, there are concerns over authorship, students’ agency in learning, and uncertainty concerning bias and misinformation. In this article, we discuss design strategies to mitigate these constraints by implementing an adults-oversight system, balancing AI-role allocation, and facilitating customization to enhance students’ agency over writing projects.

11 May 2024
Verified
Conference Paper
Open access
ZCZhenyao Cai
Zhenyao Cai
SPSeehee Park
Seehee Park
NNNia Nixon
Nia Nixon
SDShayan Doroudi
Shayan Doroudi
In today’s educational landscape, students learn collaboratively, where students benefit from both peer interactions and facilitator guidance. Prior research in Human-Computer Interaction (HCI) and Computer-Supported Collaborative Learning (CSCL) has explored chatbots and AI techniques to aid such collaboration. However, these methods often depend on predefined dialogues (which limits adaptability), are not based on collaborative learning theories, and do not fully recognize the learning context. In this paper, we introduce an Large Language Model (LLM)-powered conversational AI, designed to enhance small group learning through its advanced language understanding and generation capabilities. We detail the iterative design process, final design, and implementation. Our preliminary evaluation indicates that the bot performs as designed but points to considerations in the timing of interventions and bot’s role in discussions. The evaluation also reveals that learners perceive the bot’s tone and behavior as important for engagement. We discuss design implications for chatbot integration in collaborative learning and future research directions.

17 June 2024
Verified
Conference Paper
Open access
XZXiaofei Zhou
Xiaofei Zhou
YZYushan Zhou
Yushan Zhou
YGYunfan Gong
Yunfan Gong
ZCZhenyao Cai
Zhenyao Cai
AQAnnie Qiu
Annie Qiu
ZBZhen Bai
Zhen Bai
AI recommendations influence our daily decisions. The convenience of navigating personalized content goes hand-in-hand with the notorious filter bubble effect, which may decrease people’s exposure to diverse options and opinions. Children are especially vulnerable to this due to their limited AI literacy and critical thinking skills. In this study, we propose a novel Augmented Reality (AR) application BeeTrap. It aims to not only raise children’s awareness of filter bubbles but also empower them to mitigate this ethical issue through sense-making of AI recommendation systems’ inner workings. By having children experience and break filter bubbles in a flower recommendation system, BeeTrap utilizes embodied metaphors (e.g., NEAR-FAR, ITERATION) and analogies (bee pollination) to bridge abstract AI concepts with sensory-motor experiences in familiar STEM contexts. To evaluate our design’s effectiveness and accessibility for a broad range of children, we introduced BeeTrap in a four-day summer camp for middle-school students from underrepresented backgrounds in STEM. Results from pre- and post-tests and interviews show that BeeTrap developed students’ technical understanding of AI recommendations, empowered them to break filter bubbles, and helped them foster new personal and societal perspectives around AI technologies.


19 June 2023
Verified
Conference Paper
Open access
ZCZhenyao Cai
Zhenyao Cai
In early and middle childhood, the development of social and emotional skills is crucial. Traditional approaches often rely on curriculum-based, teacher-led methods, which may restrict children’s interactions and independent exploration. On the other hand, technology-enhanced solutions typically focus on recognizing children’s emotions without truly helping them to understand their feelings in a meaningful way. To address this gap, we introduce EmotionBlock, a novel physical toolkit with wooden blocks specifically designed for children aged 3-6. EmotionBlock encourages the development of emotional management and social skills through immersive storytelling and introspection. This hands-on approach enables children to engage in unstructured exploration and narrative creation, while simultaneously offering adults a tool to guide and support the learning experience.