An official website of the United States government
Cognitive control and rule learning are two important mechanisms that explain how goals influence behavior and how knowledge is acquired. These mechanisms are studied heavily in cognitive science literature within highly controlled tasks to understand human cognition. Although they are closely linked to the student behaviors that are often studied within intelligent tutoring systems (ITS), their direct effects on learning have not been explored. Understanding these underlying cognitive mechanisms of beneficial and harmful student behaviors can provide deeper insight into detecting such behaviors and improve predictive models of student learning. In this paper, we present a thinkaloud study where we asked students to narrate their thought processes while solving probability problems in ASSISTments. Students are randomly assigned to one of two conditions that are designed to induce the two modes of cognitive control based on the Dual Mechanisms of Control framework. We also observe how the students go through the phases of rule learning as defined in a rule learning paradigm. We discuss the effects of these different mechanisms on learning, and how the information they provide can be used in student modeling.
more »
« less
This content will become publicly available on March 1, 2026
Modeling the phases of rule learning during problem solving with an interactive learning environment
While existing student modeling methods focus on predicting students’ knowledge states, they often overlook the underlying cognitive processes contributing to learning. In this work, we integrate cognitive processes, specifically phases of rule learning, into student modeling, drawing inspiration from cognitive science. Rule learning involves rule search, discovery, and following, providing a systematic framework for understanding how individuals acquire and apply knowledge. We conduct two studies to explore rule learning phases in a real-world learning context. Moreover, we present a two-step approach to first predict the phases of rule learning students experience during problem solving with an intelligent tutoring system and then estimate the time spent on each predicted phase. Furthermore, we identify the relationships between the time spent on specific phases of rule learning and student performance. Our findings underscore the importance of integrating cognitive processes into student modeling for more targeted interventions and personalized support.
more »
« less
- Award ID(s):
- 1912474
- PAR ID:
- 10576843
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- User Modeling and User-Adapted Interaction
- Volume:
- 35
- Issue:
- 1
- ISSN:
- 0924-1868
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Cognitive control and rule learning are two important mechanisms that explain how goals influence behavior and how knowledge is acquired. These mechanisms are studied heavily in cognitive science literature within highly controlled tasks to understand human cognition. Although they are closely linked to the student behaviors that are often studied within intelligent tutoring systems (ITS), their direct effects on learning have not been explored. Understanding these underlying cognitive mechanisms of beneficial and harmful student behaviors can provide deeper insight into detecting such behaviors and improve predictive models of student learning. In this paper, we present a thinkaloud study where we asked students to narrate their thought processes while solving probability problems in ASSISTments. Students are randomly assigned to one of two conditions that are designed to induce the two modes of cognitive control based on the Dual Mechanisms of Control framework. We also observe how the students go through the phases of rule learning as defined in a rule learning paradigm. We discuss the effects of these different mechanisms on learning, and how the information they provide can be used in student modeling.more » « less
-
null (Ed.)Abstract: In the learning sciences, heterogeneity among students usually leads to different learning strategies or patterns and may require different types of instructional interventions. Therefore, it is important to investigate student subtyping, which is to group students into subtypes based on their learning patterns. Subtyping from complex student learning processes is often challenging because of the information heterogeneity and temporal dynamics. Various inverse reinforcement learning (IRL) algorithms have been successfully employed in many domains for inducing policies from the trajectories and recently has been applied for analyzing students’ temporal logs to identify their domain knowledge patterns. IRL was originally designed to model the data by assuming that all trajectories have a single pattern or strategy. Due to the heterogeneity among students, their strategies can vary greatly and the design of traditional IRL may lead to suboptimal performance. In this paper, we applied a novel expectation-maximization IRL (EM-IRL) to extract heterogeneous learning strategies from sequential data collected from three simulation environments and real-world longitudinal students’ logs. Experiments on simulation environments showed that EM-IRL can successfully identify different policies from the heterogeneous sequences with different strategies. Furthermore, experimental results from our educational dataset showed that EM-IRL can be used to obtain different student subtypes: a “learning-oriented” subtype who learned the material as much as possible regardless of the time in that they spent significantly more time than the other two subtypes and learned significantly; an“efficient-oriented”subtype who learned efficiently in that they not only learned significantly but also spent less time than the first subtype; a “no learning” subtype who spent less amount of time than first subtype and failed to learn.more » « less
-
Hands-on experiments using the Low-Cost Desktop Learning Modules (LCDLMs) have been implemented in dozens of classrooms to supplement student learning of heat transfer and fluid mechanics concepts with students of varying prior knowledge. The prior knowledge of students who encounter these LCDLMs in the classroom may impact the degree to which students learn from these interactive pedagogies. This paper reports on the differences in student cognitive learning between groups with low and high prior knowledge of the concepts that are tested. Student conceptual test results for venturi, hydraulic loss, and double pipe heat exchanger LCDLMs are analyzed by grouping the student data into two bins based on pre-test score, one for students scoring below 50% and another for those scoring above and comparing the improvement from pretest to posttest between the two groups. The analysis includes data from all implementations of each LCDLM for the 2020-2021 school year. Results from each of the three LCDLMs were analyzed separately to compare student performance on different fluid mechanics or heat exchanger concepts. Then, the overall pre- and posttest scores for all three LCDLMs were analyzed to examine how this interactive pedagogy impacts cognitive gains. Results showed statistically significant differences in improvement between low prior knowledge groups and high prior knowledge groups. Additional findings showed statistically significant results suggesting that the gaps in performance between low prior knowledge and high prior knowledge groups on pre-tests for the LCDLMs were decreased on the posttest. Findings showed that students with lower prior knowledge show a greater overall improvement in cognitive gains than those with higher prior knowledge on all three low-cost desktop learning modules.more » « less
-
Hands-on experiments using the Low-Cost Desktop Learning Modules (LCDLMs) have been implemented in dozens of classrooms to supplement student learning of heat transfer and fluid mechanics concepts with students of varying prior knowledge. The prior knowledge of students who encounter these LCDLMs in the classroom may impact the degree to which students learn from these interactive pedagogies. This paper reports on the differences in student cognitive learning between groups with low and high prior knowledge of the concepts that are tested. Student conceptual test results for venturi, hydraulic loss, and double pipe heat exchanger LCDLMs are analyzed by grouping the student data into two bins based on pre-test score, one for students scoring below 50% and another for those scoring above and comparing the improvement from pretest to posttest between the two groups. The analysis includes data from all implementations of each LCDLM for the 2020-2021 school year. Results from each of the three LCDLMs were analyzed separately to compare student performance on different fluid mechanics or heat exchanger concepts. Then, the overall pre- and posttest scores for all three LCDLMs were analyzed to examine how this interactive pedagogy impacts cognitive gains. Results showed statistically significant differences in improvement between low prior knowledge groups and high prior knowledge groups. Additional findings showed statistically significant results suggesting that the gaps in performance between low prior knowledge and high prior knowledge groups on pre-tests for the LCDLMs were decreased on the posttest. Findings showed that students with lower prior knowledge show a greater overall improvement in cognitive gains than those with higher prior knowledge on all three low-cost desktop learning modules.more » « less
