Fairness of Bayesian Knowledge Tracing for Math Learners of Different Reading Ability
Saved in:
| Title: | Fairness of Bayesian Knowledge Tracing for Math Learners of Different Reading Ability |
|---|---|
| Language: | English |
| Authors: | Frank Stinar, HaeJin Lee, Clara Belitz, Nidhi Nasiar, Stephen E. Fancsali, Steve Ritter, Husni Almoubayy, Ryan S. Baker, Jaclyn Ocumpaugh, Nigel Bosch |
| Source: | International Educational Data Mining Society. 2025. |
| Availability: | International Educational Data Mining Society. e-mail: admin@educationaldatamining.org; Web site: https://educationaldatamining.org/conferences/ |
| Peer Reviewed: | Y |
| Page Count: | 12 |
| Publication Date: | 2025 |
| Sponsoring Agency: | National Science Foundation (NSF) |
| Contract Number: | 2000638 |
| Document Type: | Speeches/Meeting Papers Reports - Research |
| Descriptors: | Mathematics Education, Bayesian Statistics, Reading Ability, Information Management, Technology Uses in Education, Individualized Instruction, Reading Achievement, Bias, Reading Comprehension, Transfer of Training |
| Abstract: | 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=0.687 and M=0.776, 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. [For the complete proceedings, see ED675583.] |
| Abstractor: | As Provided |
| Entry Date: | 2025 |
| Accession Number: | ED675619 |
| Database: | ERIC |
| Abstract: | 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=0.687 and M=0.776, 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. [For the complete proceedings, see ED675583.] |
|---|
