Search

The General Data Protection Regulation (GDPR) in the European Union contains directions on how user data may be collected, stored, and when it must be deleted. As similar legislation is developed around the globe, there is the potential for repercussions across multiple fields of research, including educational data mining (EDM). Over the past two decades, the EDM community has taken consistent steps to protect learner privacy within our research, whilst pursuing goals that will benefit their learning. However, recent privacy legislation may cause our practices to need to change. The right to be forgotten states that users have the right to request that all their data (including deidentified data generated by them) be removed. In this paper, we discuss the potential challenges of this legislation for EDM research, including impacts on Open Science practices, data modeling, and data sharing. We also consider changes to EDM best practices that may aid compliance with this new legislation. [For the complete proceedings, see ED630829.]

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. [For the complete proceedings, see ED630829.]

Construction is a critical player in the U.S. economy. Construction contributed $884 billion to the nation's GDP in 2019, employing more than 7.5 million people in the United States. Despite its prominent role in the national economy, the construction industry still deals with long-standing problems. Construction project managers (CPMs) are critical to resolving many of these problems. Identifying training gaps in construction project management requires a deep awareness of the necessary competencies. The authors identified 21 skills required for CPMs and revealed essential knowledge areas and personality characteristics critical to each skill. A survey including 672 ranking questions was developed to explore the global construction academics' perception of the importance of each knowledge area/personality characteristic to each skill. Each participant ranked the importance of two universal knowledge areas, two domain-specific knowledge areas, and three personality characteristics to three skills. The data was collected from 2,016 construction academics worldwide. This paper focuses on the ability to create written and oral communications appropriate to the construction discipline. The findings can assist the construction academia in directing their efforts toward key competency development areas, and scaffolding courses and planning curricula to the real needs of the worldwide workforce. [For the full proceedings, see ED656038.]

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. [This paper was published in: "Proceedings of the 16th International Conference on Educational Data Mining," edited by M. Feng et al., International Educational Data Mining Society, 2023, pp. 207-16.]

Large Language Models have recently achieved high performance on many writing tasks. In a recent study, math word problems in Carnegie Learning's MATHia adaptive learning software were rewritten by human authors to improve their clarity and specificity. The randomized experiment found that emerging readers who received the rewritten word problems spent less time completing the problems and also achieved higher mastery compared to emerging readers who received the original content. We used GPT-4 to rewrite the same set of math word problems, prompting it to follow the same guidelines that the human authors followed. We lay out our prompt engineering process, comparing several prompting strategies: zero-shot, few-shot, and chain-of-thought prompting. Additionally, we overview how we leveraged GPT's ability to write python code in order to encode mathematical components of word problems. We report text analysis of the original, human-rewritten, and GPT-rewritten problems. GPT rewrites had the most optimal readability, lexical diversity, and cohesion scores but used more low frequency words. We present our plan to test the GPT outputs in upcoming randomized field trials in MATHia.

In this study, we sought to understand what might be learned about preservice teachers' mathematics learner and mathematics educator identities in the context of a problem-solving focused mathematics content course. Twenty-two preservice teachers participated in this study as part of their undergraduate teacher preparation program. We implemented a narrative identity lens which operationalized stories as identity with a sociocultural understanding of learning. In our findings we discuss examples of how mathematics learner identity influenced mathematics educator identity, and vice versa. In addition, we emphasize the importance of the way that preservice teachers define mathematics and how this influences mathematics identities. [For the complete proceedings, see ED657822.]

Data literacy is the ability to collect, manage, evaluate, and apply data, in a critical manner. It is a relatively new field of study, dating only from the 2010s. It includes the skills necessary to discover and access data, manipulate data, evaluate data quality, conduct analysis using data, interpret results of analyses, and understand the ethics of using data. This paper considers data literacy education across three frameworks: the competency model defining data literacy, the assessment of data literacy competencies, and methods for the development of data literacy in an organization. These principles are applied to a discussion of the development of an open online course supporting the development of data literacy in the form of a corresponding data structure encompassing the three frameworks identified in the literature. [For the full proceedings, see ED636095.]

Research into "gaming the system" behavior in intelligent tutoring systems (ITS) has been around for almost two decades, and detection has been developed for many ITSs. Machine learning models can detect this behavior in both real-time and in historical data. However, intelligent tutoring system designs often change over time, in terms of the design of the student interface, assessment models, and data collection log schemas. Can gaming detectors still be trusted, a decade or more after they are developed? In this research, we evaluate the robustness/degradation of gaming detectors when trained on older data logs and evaluated on current data logs. We demonstrate that some machine learning models developed using past data are still able to predict gaming behavior from student data collected 16 years later, but that there is considerable variance in how well different algorithms perform over time. We demonstrate that a classic decision tree algorithm maintained its performance while more contemporary algorithms struggled to transfer to new data, even though they exhibited better performance on unseen students in both New and Old data sets by themselves. Examining the feature importance values provides some explanation for the differences in performance between models, and offers some insight into how we might safeguard against detector rot over time. [For the full proceedings, see ED623995.]

Black Americans are uniquely placed within the phenomenon of American elections. In this conversation between Chris McAuley, Black Studies Collection Editor at Lived Places Publishing and Stephen Graves, author of [*At War With Politics: A Journey from Traditional Political Science to Black Politics*](https://livedplacespublishing.com/book/isbn/9781915271112?utm_source=MB&utm_medium=cassyni&utm_campaign=black-studies&utm_content=Graves), they examine the upcoming U.S. presidential election through the lens of Black politics. When situated within the “struggle” of Black politics, each election presents new opportunities with familiar adversaries and potential consequences. The “struggle” is twofold: 1) African Americans’ attempts for racial, social, and economic justice while simultaneously struggling against 2) the white dominant majority’s maintenance of power, the ability to find viable coalitions with other oppressed and disadvantaged groups, and to see their policy preferences turn into real policy. In the upcoming election, new issues such as the weaponization of DEI will replace older strategies scapegoating Black Americans for the declining standing of white Americans. American elections demand that African Americans prepare for the worst regardless of the electoral outcome: Either they become symbols of America’s decline and the depleting influence of white America or witness any progress they’ve made get stripped away. Ultimately, this seminar hopes to revisit traditional strategies while offering insight to new possibilities for Black politics.

The familiar divergence and Kelvin–Stokes theorem are generalized by a tensor-valued identity that relates the volume integral of the gradient of a vector field to the integral over the bounding surface of the tensor product of the vector field with the exterior normal. The importance of this long-established yet relatively little-known result is discussed. In flat two-dimensional space, it reduces to a relationship between an integral over an area and that over its bounding curve, combining the two-dimensional divergence and Kelvin–Stokes theorems together with two related theorems involving the strain, as is shown through a decomposition using a suitable tensor basis. A fluid dynamical application to oceanic observations along the trajectory of a moving platform is given. The potential extension of the generalized two-dimensional identity to curved surfaces is considered and is shown not to hold. Finally, the paper includes a substantial background section on tensor analysis, and presents results in both symbolic notation and index notation in order to emphasize the correspondence between these two notational systems.

Self-regulated learning (SRL) is a critical component of mathematics problem solving. Students skilled in SRL are more likely to effectively set goals, search for information, and direct their attention and cognitive process so that they align their efforts with their objectives. An influential framework for SRL, the SMART model, proposes that five cognitive operations (i.e., searching, monitoring, assembling, rehearsing, and translating) play a key role in SRL. However, these categories encompass a wide range of behaviors, making measurement challenging -- often involving observing individual students and recording their think-aloud activities or asking students to complete labor-intensive tagging activities as they work. In the current study, we develop machine-learned indicators of SMART operations, in order to achieve better scalability than other measurement approaches. We analyzed student's textual responses and interaction data collected from a mathematical learning platform where students are asked to thoroughly explain their solutions and are scaffolded in communicating their problem-solving process to their peers and teachers. We built detectors of four indicators of SMART operations (namely, assembling and translating operations). Our detectors are found to be reliable and generalizable, with AUC ROCs ranging from 0.76-0.89. When applied to the full test set, the detectors are robust against algorithmic bias, performing well across different student populations. [For the full proceedings, see ED623995.]

Ten years after the announcement of the "rise of the super experiment" at Educational Data Mining 2012, challenges to implementing "internet scale" educational experiments often persist for educational technology providers, especially when they seek to test substantive instructional interventions. Studies that deploy and test interventions, when informed by data-driven modeling, are often described as "close the loop" studies. Studies that close the loop attempt to link improvements in statistical and machine learning models of learning to real-world learning outcomes. After first considering challenges to internet scale experiments, we review several educational data science/mining studies that close the loop between data-driven modeling and learning outcomes. Next, we describe UpGrade, an open source architecture that, when integrated with educational technologies, helps overcome challenges to large-scale field trials (or internet scale experiments) that close the loop between data-driven work and real-world learning outcomes. In addition to describing preliminary randomized experiments that have been conducted and will soon be conducted using the architecture in two educational technology platforms, we end with a "call for contributors and integrators." UpGrade contributors and integrators will be researchers and developers who seek to drive continuous, data-driven improvements in real-world settings where learning with technology occurs. [For the full proceedings, see ED623995.]

This study reports on the development, validation, and reliability of a geometry disposition scale (GDS) to measure pre-service teachers' (PSTs') attitudes to geometry learning. PSTs from two Colleges of Education (CoEs) in Ghana volunteered to participate in the study (N = 153). A principal component analysis (PCA) extracted four factors: deep affect (positivity expressed towards geometry learning), working privately, collaborative working and technology or calculator use. The final GDS contained 15 items. While validation is still not fully tested, the psychometric properties to-date suggest the GDS has promising benefits in measuring PSTs' attitudes to geometry learning, which may enable the adjustment of the teaching of geometry accordingly.

Mathematics self-efficacy is considered an important variable in mathematics education because of its links to mathematics achievement. This paper reports on the development of the "Self-efficacy-effort in Mathematics Scale" (SEEMS), an instrument that has strong theoretical and psychometric properties. Based on a sample of n = 224 Australian primary students and n =133 secondary students, the instrument demonstrated positive correlations with related measures of mathematics achievement and mathematics self-concept. Girls had higher mathematics achievement within the primary and secondary school data. There were no significant gender difference in mathematic self-concept scores for the primary and the secondary school students. For mathematics self-efficacy, a gender difference was only identified in the high school data. The implications of this research to mathematics education practices are reviewed in the paper.