skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on July 14, 2026

Title: Fairness of Bayesian Knowledge Tracing for Math Learners of Different Reading Ability
Students' reading ability affects their outcomes in learning software even outside of reading education, such as in math education, which can result in unexpected and inequitable outcomes. We analyze an adaptive learning software using Bayesian Knowledge Tracing (BKT) to understand how the fairness of the software is impacted when reading ability is not modeled. We tested BKT model fairness by comparing two years of data from 8,549 students who were classified as either "emerging" or "non-emerging" readers (i.e., a measure of reading ability). We found that while BKT was unbiased on average in terms of equal predictive accuracy across groups, specific skills within the adaptive learning software exhibited bias related to reading level. Additionally, there were differences between the first-answer mastery rates of the emerging and non-emerging readers (M=.687 and M=.776, difference CI=[0.075, 0.095]), indicating that emerging reader status is predictive of mastery. Our findings demonstrate significant group differences in BKT models regarding reading ability, exhibiting that it is important to consider—and perhaps even model—reading as a separate skill that differentially influences students' outcomes."]}  more » « less
Award ID(s):
2000638
PAR ID:
10658125
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ;
Editor(s):
Mills, Caitlin; Alexandron, Giora; Taibi, Davide; Lo_Bosco, Giosuè; Paquette, Luc
Publisher / Repository:
International Educational Data Mining Society
Date Published:
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Proceedings of the 16th International Conference on Educational Data Mining)
    Feng, Mingyu; Käser, Tanja; Talukdar, Partha (Ed.)
    Recent research seeks to develop more comprehensive learner models for adaptive learning software. For example, models of reading comprehension built using data from students’ use of adaptive instructional software for mathematics have recently been developed. These models aim to deliver experiences that consider factors related to learning beyond performance in the target domain for instruction. We investigate the extent to which generalization is possible for a recently developed predictive model that seeks to infer students’ reading comprehension ability (as measured by end-of-year standardized test scores) using an introductory learning experience in Carnegie Learning’s MATHia intelligent tutoring system for mathematics. Building on a model learned on data from middle school students in a single school district in a mid-western U.S. state, using that state’s end-of-year English Language Arts (ELA) standardized test score as an outcome, we consider data from a school district in a south-eastern U.S. state as well as that state’s end-of-year ELA standardized test outcome. Generalization is explored by considering prediction performance when training and testing models on data from each of the individual school districts (and for their respective state’s test outcomes) as well as pooling data from both districts together. We conclude with discussion of investigations of some algorithmic fairness characteristics of the learned models. The results suggest that a model trained on data from the smaller of the two school districts considered may achieve greater fairness in its predictions over models trained on data from the other district or both districts, despite broad, overall similarities in some demographic characteristics of the two school districts. This raises interesting questions for future research on generalizing these kinds of models as well as on ensuring algorithmic fairness of resulting models for use in real-world adaptive systems for learning. 
    more » « less
  2. ; ; ; ; (, International Educational Data Mining Society)
    Mills, Caitlin; Alexandron, Giora; Taibi, Davide; Lo_Bosco, Giosuè; Paquette, Luc (Ed.)
    Recent research on more comprehensive models of student learning in adaptive math learning software used an indicator of student reading ability to predict students' tendencies to engage in behaviors associated with so-called "gaming the system." Using data from Carnegie Learning's MATHia adaptive learning software, we replicate the finding that students likely to experience reading difficulties are more likely to engage in behaviors associated with gaming the system. Using both observational and experimental data, we consider relationships between student reading ability, readability of specific math lessons, and behavior associated with gaming. We identify several readability characteristics of specific content that predict detected gaming behavior, as well as evidence that a prior experiment that targeted enhanced content readability decreased behavior associated with gaming, but only for students that are predicted to be less likely to experience reading difficulties. We suggest avenues for future research to better understand and model behavior of math learners, especially those who may be experiencing reading difficulties while they learn math. 
    more » « less
  3. ; (, Zone 1 Conference of the American Society for Engineering Education)
    This theory paper focuses on understanding how mastery learning has been implemented in undergraduate engineering courses through a systematic review. Academic environments that promote learning, mastery, and continuous improvement rather than inherent ability can promote performance and persistence. Scholarship has argued that students could achieve mastery of the course material when the time available to master concepts and the quality of instruction was made appropriate to each learner. Increasing time to demonstrate mastery involves a course structure that allows for repeated attempts on learning assessments (i.e., homework, quizzes, projects, exams). Students are not penalized for failed attempts but are rewarded for achieving eventual mastery. The mastery learning approach recognizes that mastery is not always achieved on first attempts and learning from mistakes and persisting is fundamental to how we learn. This singular concept has potentially the greatest impact on students’ mindset in terms of their belief they can be successful in learning the course material. A significant amount of attention has been given to mastery learning courses in secondary education and mastery learning has shown an exceptionally positive effect on student achievement. However, implementing mastery learning in an undergraduate course can be a cumbersome process as it requires instructors to significantly restructure their assignments and exams, evaluation process, and grading practices. In light of these challenges, it is unclear the extent to which mastery learning has been implemented in undergraduate engineering courses or if similar positive effects can be found. Therefore, we conducted a systematic review to elucidate, how in the U.S., (1) has mastery learning been implemented in undergraduate engineering courses from 1990 to the present time and (2) the student outcomes that have been reported for these implementations. Using the systematic process outlined by Borrego et al. (2014), we surveyed seven databases and a total of 584 articles consisting of engineering and non-engineering courses were identified. We focused our review on studies that were centered on applying the mastery learning pedagogical method in undergraduate engineering courses. All peer-reviewed and practitioner articles and conference proceedings that were within our scope were included in the synthetization phase of the review. Most articles were excluded based on our inclusion and exclusion criteria. Twelve studies focused on applying mastery learning to undergraduate engineering courses. The mastery learning method was mainly applied on midterm exams, few studies used the method on homework assignments, and no study applied the method to the final exam. Students reported an increase in learning as a result of applying mastery learning. Several studies reported that students’ grades in a traditional final exam were not affected by mastery learning. Students’ self-reported evaluation of the course suggests that students prefer the mastery learning approach over traditional methods. Although a clear consensus on the effect of the mastery learning approach could not be achieved as each article applied different survey instruments to capture students’ perspectives. Responses to open-ended questions have mixed results. Two studies report more positive student comments on opened-ended questions, while one study report receiving more negative comments regarding the implementation of the mastery learning method. In the full paper we more thoroughly describe the ways in which mastery learning was implemented along with clear examples of common and divergent student outcomes across the twelve studies. 
    more » « less
  4. ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    Predictive analytics has been widely used in various domains, including education, to inform decision-making and improve outcomes. However, many predictive models are proprietary and inaccessible for evaluation or modification by researchers and practitioners, limiting their accountability and ethical design. Moreover, predictive models are often opaque and incomprehensible to the officials who use them, reducing their trust and utility. Furthermore, predictive models may introduce or exacerbate bias and inequity, as they have done in many sectors of society. Therefore, there is a need for transparent, interpretable, and fair predictive models that can be easily adopted and adapted by different stakeholders. In this paper, we propose a fair predictive model based on multivariate adaptive regression splines (MARS) that incorporates fairness measures in the learning process. MARS is a non-parametric regression model that performs feature selection, handles non-linear relationships, generates interpretable decision rules, and derives optimal splitting criteria on the variables. Specifically, we integrate fairness into the knot optimization algorithm and provide theoretical and empirical evidence of how it results in a fair knot placement. We apply our fairMARS model to real-world data and demonstrate its effectiveness in terms of accuracy and equity. Our paper contributes to the advancement of responsible and ethical predictive analytics for social good. 
    more » « less
  5. ; ; ; ; ; (, ACM)
    Introduction: The emergence and widespread adoption of generative AI (GenAI) chatbots such as ChatGPT, and programming assistants such as GitHub Copilot, have radically redefined the landscape of programming education. This calls for replication of studies and reexamination of findings from pre-GenAI CS contexts to understand the impact on students. Objectives: Achievement Goals are well studied in computing education and can be predictive of student interest and exam performance. The objective in this study is to compare findings from prior achievement goal studies in CS1 courses with new CS1 courses that emphasize the use of human-GenAI collaborative coding. Methods: In a CS1 course that integrates GenAI, we use linear regression to explore the relationship between achievement goals and prior experience on student interest, exam performance, and perceptions of GenAI. Results: As with prior findings in traditional CS1 classes, Mastery goals are correlated with interest in computing. Contradicting prior CS1 findings, normative goals are correlated with exam scores. Normative and mastery goals correlate with students’ perceptions of learning with GenAI. Mastery goals weakly correlate with reading and testing code output from GenAI. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email