Kexin Bella Yang

Kexin Bella Yang

Auto-generated profile, based on publicly available information

Kexin Bella Yang

Carnegie Mellon University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
19 April 2023
Verified
Conference Paper
Open access
KYKexin Bella Yang
Kexin Bella Yang
VEVanessa Echeverria
Vanessa Echeverria
ZLZijing Lu
Zijing Lu
HMHongyu Mao
Hongyu Mao
KHKenneth Holstein
Kenneth Holstein
VAVincent Aleven
Vincent Aleven
Enabling students to dynamically transition between individual and collaborative learning activities has great potential to support better learning. We explore how technology can support teachers in orchestrating dynamic transitions during class. Working with five teachers and 199 students over 22 class sessions, we conducted classroom-based prototyping of a co-orchestration technology ecosystem that supports the dynamic pairing of students working with intelligent tutoring systems. Using mixed-methods data analysis, we study the resulting observed classroom dynamics, and how teachers and students perceived and experienced dynamic transitions as supported by our technology. We discover a potential tension between teachers’ and students’ preferred level of control: students prefer a degree of control over the dynamic transitions that teachers are hesitant to grant. Our study reveals design implications and challenges for future human-AI co-orchestration in classroom use, bringing us closer to realizing the vision of highly-personalized smart classrooms that address the unique needs of each student.

23 February 2023 in IEEE Transactions on Learning Technologies
Verified
Journal Article
Closed access
VEVanessa Echeverria
Vanessa Echeverria
KYKexin Yang
Kexin Yang
LLLuEttaMae Lawrence
LuEttaMae Lawrence
NRNikol Rummel
Nikol Rummel
VAVincent Aleven
Vincent Aleven
Combining individual and collaborative learning is common, but dynamic combinations (which happen as-the-need arises, rather than in pre-planned ways, and may happen on an individual basis) are rare. This work reports findings from a technology probe study exploring alternative designs for classroom co-orchestration support for dynamically transitioning between individual and collaborative learning. The study involved 1) a technology-probe classroom study in an authentic, AI-supported classroom to understand teachers' and students' needs for co-orchestration support over dynamic transitions; and 2) workshops and interviews with students and teachers to get informed feedback about their lived experiences. 118 students and three teachers from a middle school in the US experienced a pairing policy – student, teacher and, AI-controlled pairing policy – (i.e., identifying students needing help and potential helpers) for switching from individual to a peer tutoring activity. This work aims to answer the following questions: 1) How did students and teachers react to these pairing policies?; and 2) What are students' and teachers' desires for sharing control over the orchestration of dynamic transitions? Findings suggest the need for a form of hybrid control between students, teachers, and AI systems over transitions, as well as for adaptivity and adaptability for different classroom characteristics, teachers, and students' prior knowledge.

9 September 2021
Verified
Book Chapter
Closed access
PDF file
KYKexin Bella Yang
Kexin Bella Yang
LLLuEttaMae Lawrence
LuEttaMae Lawrence
VEVanessa Echeverria
Vanessa Echeverria
BGBoyuan Guo
Boyuan Guo
NRNikol Rummel
Nikol Rummel
VAVincent Aleven
Vincent Aleven

8 May 2024 in EdArXiv
Verified
Preprint
Open access
CBConrad Borchers
Conrad Borchers
KYKexin Yang
Kexin Yang
JLJionghao Lin
Jionghao Lin
NRNikol Rummel
Nikol Rummel
KKKenneth R. Koedinger
Kenneth R. Koedinger
VAVincent Aleven
Vincent Aleven
Peer tutoring can improve learning by prompting learners to reflect. To assess whether peer interactions are conducive to learning and provide peer tutoring support accordingly, what tutorial dialog types relate to student learning most? Advancements in collaborative learning analytics allow for merging machine learning-based dialog act classification with cognitive modeling of fine-grained learning processes during problem-solving to illuminate this question. We estimate how much peer-tutored students improve in a collaborative tutoring system for linear equation-solving in K-12 mathematics in relationship to the peer dialog types they engage in. This work establishes a reliable BERT classifier with an accuracy of close to 80\% to classify chat messages during peer tutoring into minimal, facilitative, and constructive, serving as instructional factors. Based on data from 394 students, peer tutor dialog was rare. Only 8\% of tutee problem-solving steps were followed by peer tutor chat messages. Still, facilitative tutor dialog was associated with an increased tutee learning rate. Meanwhile, tutor dialog classified as constructive was associated with lower learning rates. Content analysis suggested that such dialog often reinforced incorrect solutions, gave away answers, or was unrelated to the taught content. Hence, considering problem-solving solution contexts could improve the assessment of peer tutoring dialog. Peer tutors engaging in little dialog could be attributed to the high cognitive demand of learning to tutor while still learning the content they tutor on. Providing peer tutors with instructional support to engage in constructive dialog may improve the tutee's learning.