Yan Ping Xin

Educational laws and current standards emphasize fostering conceptual understanding in problem-solving, as well as cultivating higher-order thinking and reasoning skills, with the ultimate goal of developing independent mathematical thinkers. The purpose of this study, conducted at a Midwest U.S. elementary school, was to explore the impact of the Please Go Bring Me-COnceptual Model-based Problem-Solving intelligent tutor on word problem-solving skills and multiplicative concept development of students with learning disabilities or difficulties in mathematics. The multiple-probe across-participants design was used to explore the functional relationship between the intervention program and students’ problem-solving skills and the development of conceptual knowledge. Concept development was measured by the levels of independence in solving problems provided by the intelligent tutor. Results showed that the tutoring system was effective in promoting students’ critical thinking and word problem-solving performance. It seems that features, such as the guided discovery strategy embedded in the tutoring system may have contributed to students’ development as an independent problem solver.

This study examined how to support implementation agents in establishing and maintaining the implementation fidelity (IF) of a mathematics evidence-based practice (EBP) for Tier 2 instruction in a rural Midwestern U.S. school. Tier 2 interventions, which serve students at risk of academic failure, play a critical role in bridging general and special education. However, their effectiveness is often hindered by low IF—the degree to which interventions are delivered as intended. This mixed-methods sequential explanatory study employed a multiple-baseline single-subject design in Phase 1 to evaluate the effects of an IF intervention package on participants’ fidelity to a Tier 2 word problem-solving intervention. Semi-structured interviews in Phase 2 explored participants’ experiences with the intervention and examined contextual factors influencing EBP implementation in rural settings. The findings underscore the importance of understanding rural school contexts and providing structured supports to enhance the implementation of mathematics EBPs in these settings.

Over the past decade, the mathematical performance of at-risk students has not improved and has, in fact, declined since 2020. Conceptual Model-Based Problem-Solving (COMPS) strategies have been studied by researchers in and outside of the U.S. To date, there is no systematic review evaluating this body of research. The purpose of this study was to conduct a systematic review evaluating the quality and evidence base of research studies that utilized COMPS strategies in helping students learn mathematics. A total of 20 studies involving students with disabilities or learning difficulties in mathematics, with grade levels ranging from third to eighth grade, were included in this review. We used Council for Exceptional Children quality indicators and What Works Clearinghouse standards to evaluate the methodology rigor of this body of research and determine the evidence base of the COMPS strategies. The results of this systematic review of the evidence base indicate that COMPS is an evidence-based practice particularly based on the single-case design studies identified in this review. Implications for future research and practices are discussed in the context of paradigm shifts in mathematics teaching and learning.

Educational process data offers valuable opportunities to enhance teaching and learning by providing more detailed insights into students’ learning and problem-solving processes. However, its large size, unstructured format, and inherent noise pose significant challenges for effective analysis. Machine learning (ML) has emerged as a powerful tool for tackling such complexities. Despite growing interest, a comprehensive review of ML applications in process data analysis remains lacking. This study contributes to the literature by systematically reviewing 38 peer-reviewed publications, dated from 2013 to 2024, following PRISMA 2020 guidelines. The findings of this review indicate that (1) clickstream data is the most widely used processing data type, (2) process data analysis offers actionable insights to support differentiated instruction and address diverse student needs, and (3) ML typically serves as a tool for coding process data or estimating student ability. Persistent challenges, including feature extraction and interpreting results for practical applications, are also discussed. Finally, implications for future research and practice are discussed with a focus on enhancing personalized learning, improving assessment accuracy, and promoting test fairness.

With the development of high-performance computers, cloud storage, and advanced sensors, people’s ability to gather complex learning data has greatly improved. However, analyzing these data remains a significant challenge. Especially for spatiotemporal learning data such as eye-tracking and mouse movement, understanding and analyzing these data to identify the learning insights behind them is a difficult task. We propose a visualization platform called “MultiScaleAnalyzer”, which employs hierarchical structure to illustrate spatiotemporal learning data in multiple views. From high-level overviews to detailed analyses, “MultiScaleAnalyzer” provides varying resolutions of data tailored to educators’ need. To demonstrate the platform’s effectiveness, we applied “MultiScaleAnalyzer” to a mathematical word problem-solving dataset, showcasing how the visualization platform facilitates the exploration of student problem-solving patterns and strategies.

The aim of this meta-analysis was to investigate the effect of technology-based interventions on mathematical word problem solving for students with disabilities. This study also assessed the quality of research based on What Works Clearinghouse (WWC) design standards. A total of 21 studies were included in the analysis. This study computed an overall effect and analyzed moderators of group design studies (Hedges’ g) and single-case design studies (between-case standardized mean difference) in the same analyses. The results show that the overall effect of technology-based interventions on word problems across 21 studies was large (Hedges’ g = 1.18, 95% CI = 0.84, 1.52). Additionally, the studies meeting WWC design standards demonstrated significantly greater effects. The moderator analyses indicated that certain study characteristics, such as publication years, settings, intervention agents, technology devices and types, and mathematics topics moderated the effects of interventions. The four studies that evaluated the generalization effect of the intervention using distal standardized assessments showed a near moderate effect (Hedges’ g = 0.49, 95% CI = 0.09, 0.9). Implications for future research and practice are discussed.