Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bo Pei has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Engaging Secondary Students in Data Science Learning Through a Mathematical Logic Approach: Insights from Surveys and Log Data

    by Zifeng Liu, Wanli Xing, Barnas Monteith, Bo Pei, Yuanlin Zhang

    Data science education is becoming increasingly important in both K–12 and higher education. However, due to its interdisciplinary complexity, providing a high-quality and accessible open curriculum for K–12 students remains a challenge. Although many data science curricula have been developed for higher education, their topics and prerequisite knowledge often make them inappropriate for K–12 learners. As a critical pathway for preparing students with relevant skills, data science education for K–12 should be built on a rigorous foundation that integrates mathematics, statistics and programming. In this study, we designed and developed a logic-based data science curriculum aimed at engaging secondary school students through online learning and the use of student-relevant examples. We implemented a one-week pilot version consisting of six lessons and recruited 110 self-selected participants. To investigate student engagement and learning behaviors, we collected pre-surveys, end-of-lesson surveys, quiz responses, post-surveys, and learning management system (LMS) activity logs. Findings suggest that: (1) students generally engaged with the logic-based data science curriculum; (2) students from diverse academic and cultural backgrounds reported broadly similar experiences with the curriculum; and (3) entropy-based behavioral measures helped describe students’ LMS activity patterns, although average entropy was not significantly associated with quiz performance and the negative association between entropy CoV (coefficient of variation) and quiz performance was on the border of significance. This study offers preliminary empirical insights into the design, development and implementation of data science education for K–12 learners.

  • Top Cited Papers
    Open Access

    Enhancing AI literacy for educators: Where to start and to what end?

    by Bo Pei, Jie Lu, Zhaowei Zhang, Priscilla Tuffour, Sanghoon Park


  • Open Access

    Balancing Act

    by Alison Cheng, Bo Pei, Cheng Liu

    Machine learning algorithms have been widely used for identifying at-risk students. Current research focuses on timeliness and accuracy of the predictions, leading to a heavy reliance on demographic data, which introduces severe bias issues. This study develops fairness-aware machine learning models to identify at-risk students in high school Advanced Placement (AP) statistics, where student performance is closely linked to demographic background. We evaluated the predictive performance and bias mitigation strategies of various machine learning algorithms. To determine the optimal time for accurate and fair identification of at-risk students, we divided the dataset into three stages corresponding to the course’s progress. At each stage, we examined model performance and fairness across groups defined by race, gender, and eligibility for free/reduced-price lunch. Our findings suggest that at Stage 1 (i.e., up to the first unit review assignment), the models effectively identified at-risk students while maintaining fairness across demographic groups. We discovered that incorporating more learning activity data reduced the potential bias caused by overreliance on demographic information. We also examined the impact of different bias mitigation approaches as well as the exclusion of the sensitive features on predictive accuracy and fairness. We further discuss their implications for designing more context-specific solutions in educational settings.


  • Open Access

    Unveiling Accuracy-Fairness Trade-Offs

    by Raymond A. Opoku, Bo Pei, Wanli Xing

    While high-accuracy machine learning (ML) models for predicting student learning performance have been widely explored, their deployment in real educational settings can lead to unintended harm if the predictions are biased. This study systematically examines the trade-offs between prediction accuracy and fairness in ML models trained on the widely used Open University Learning Analytics Dataset (OULAD). We evaluated the relationship between model accuracy and fairness across various student demographic subgroups and investigated the extent to which fairness can be improved without significantly sacrificing accuracy. Our analysis revealed that standard ML models often exhibit bias; however, applying bias mitigation techniques can reduce these disparities while maintaining acceptable accuracy. Our findings emphasize the importance of auditing ML models for fairness to ensure that predictive insights are equitable across diverse student populations. We also discuss implications for best practices and challenges in achieving fair ML models for student performance prediction.


  • Open Access

    Understanding Students’ Learning Motivations in Online Learning Settings: From a Quantitative Perspective

    by Bo Pei

    This study investigates the role of learning motivation as a significant predictor of learning performance in online learning environments. Grounded in the Self-Determination Theory (SDT), we explored approaches to conceptualize, construct, and validate quantifiable indicators of student learning motivations in online learning settings. Traditional approaches, like surveys and questionnaires, rely heavily on self-reported data, making it challenging to characterize students’ learning motivations objectively and detect the corresponding dynamics over time. This study explores an approach to quantify students’ learning motivations based on online learning activities with the aim to profile students’ learning motivations objectively and dynamically. We employed clustering approaches to group students into different motivation groups based on those extracted learning activities. Multiple statistical approaches and machine learning approaches were adopted to validate the effectiveness of the proposed motivation quantifying metrics. The analytical results indicate that students’ learning motivation can be effectively modeled through students’ online learning activities, even at an early stage in the learning process. This study contributes to the field by providing insights for quantifying students’ learning motivations and detecting their dynamics in learning in virtual learning environments. Practical recommendations include optimizing instructional strategies that focus on activities that impact motivation and offering targeted support according to motivation categories. Future research will focus on validating the proposed metrics across various learning settings and further investigate fine-grained factors that influence students’ learning motivations.


  • Open Access

    Live Coding Prompts Engagement, But Not Necessarily Grades

    by Hanxiang Du, Dion Udokop, Bo Pei

    Live coding has gained its prominence in Computer Science (CS) classrooms as it enhances learning experiences by providing real-time demonstrations of programming and debugging during lectures. However, live coding may also present challenges to the effectiveness and inclusiveness of the classroom environment. This experience report presents the use of live coding in an introductory level CS course to better understand its impact on novice learners and their perceptions of the strategy. We conducted a between-subjects study at a public university in the United States across two course offerings. Specifically, the instructor taught the same course in two consecutive quarters: one with live coding and one without. Through assignment and exam scores, grades, and surveys, we compared data from students who experienced live coding with those who did not. We found that while live coding prompted engagement and interaction, and students believed that it helped them learn better, there was no statistically significant difference in course performance in terms of assignment and exam scores, nor in final grades. Additionally, most students prefer to keep live coding in lectures despite the challenges it presents. We also shared challenges, lessons, and practical instructional strategies learned from this experience, in the hope that they will contribute to developing more engaging and inclusive learning experiences in CS classrooms.