Search for: All records

Teachers often use open-ended questions to promote students' deeper understanding of the content. These questions are particularly useful in K–12 mathematics education, as they provide richer insights into students' problem-solving processes compared to closed-ended questions. However, they are also challenging to implement in educational technologies as significant time and effort are required to qualitatively evaluate the quality of students' responses and provide timely feedback. In recent years, there has been growing interest in developing algorithms to automatically grade students' open responses and generate feedback. Yet, few studies have focused on augmenting teachers' perceptions and judgments when assessing students' responses and crafting appropriate feedback. Even fewer have aimed to build empirically grounded frameworks and offer a shared language across different stakeholders. In this paper, we propose a taxonomy of feedback using data mining methods to analyze teacher-authored feedback from an online mathematics learning platform. By incorporating qualitative codes from both teachers and researchers, we take a methodological approach that accounts for the varying interpretations across coders. Through a synergy of diverse perspectives and data mining methods, our data-driven taxonomy reflects the complexity of feedback content as it appears in authentic settings. We discuss how this taxonomy can support more generalizable methods for providing pedagogically meaningful feedback at scale. 

Stream metabolism, encompassing gross primary production and ecosystem respiration, reflects the fundamental energetic dynamics of freshwater ecosystems. These processes regulate the concentrations of dissolved gases like oxygen and carbon dioxide, which in turn shape aquatic food webs and ecosystem responses to stressors such as floods, drought, and nutrient loading. Historically difficult to quantify, stream metabolism is now measurable at high temporal resolution thanks to advances in sensor technology and modeling. The StreamPULSE dataset includes high-frequency sensor data, metadata, and modeled estimates of ecosystem metabolism. This living dataset contributes to a growing body of open-access data characterizing the metabolic pulse of stream ecosystems worldwide. To contribute to StreamPULSE, visit data.streampulse.org. All data contributed to StreamPULSE become public after an optional embargo period. Use this publication to access annual data releases, or use data.streampulse.org to download new data as they become available. 

Abstract This study evaluates a popular density current propagation speed equation using a large, novel set of radiosonde and dropsonde observations. Data from pairs of sondes launched inside and outside of cold pools along with the theoretical density current propagation speed equation are used to calculate sonde-based propagation speeds. Radar-/satellite-based propagation speeds, assumed to be the truth, are calculated by manually tracking the propagation of cold pools and correcting for advection due to the background wind. Several results arise from the comparisons of the theoretical sonde-based speeds with the radar-/satellite-based speeds. First, sonde-based and radar-based propagation speeds are strongly correlated for U.S. High Plains cold pools, suggesting the density current propagation speed equation is appropriate for use in midlatitude continental environments. Second, cold pool Froude numbers found in this study are in agreement with previous studies. Third, sonde-based propagation speeds are insensitive to how cold pool depth is defined since the preponderance of negative buoyancy is near the surface in cold pools. Fourth, assuming an infinite channel depth and assuming an incompressible atmosphere when deriving the density current propagation speed equation can increase sonde-based propagation speeds by up to 20% and 11%, respectively. Finally, sonde-based propagation speeds can vary by ∼300% based on where and when the sondes were launched, suggesting submesoscale variability could be a major influence on cold pool propagation. 

The educational data mining community has extensively investigated affect detection in learning platforms, finding associations between affective states and a wide range of learning outcomes. Based on these insights, several studies have used affect detectors to create interventions tailored to respond to when students are bored, confused, or frustrated. However, these detector-based interventions have depended on detecting affect when it occurs and therefore inherently respond to affective states after they have begun. This might not always be soon enough to avoid a negative experience for the student. In this paper, we aim to predict students' affective states in advance. Within our approach, we attempt to determine the maximum prediction window where detector performance remains sufficiently high, documenting the decay in performance when this prediction horizon is increased. Our results indicate that it is possible to predict confusion, frustration, and boredom in advance with performance over chance for prediction horizons of 120, 40, and 50 seconds, respectively. These findings open the door to designing more timely interventions. 

Abstract Modeling Arctic-Boreal vegetation is a challenging but important task, since this highly dynamic ecosystem is undergoing rapid and substantial environmental change. In this work, we synthesized information on 18 dynamic vegetation models (DVMs) that can be used to project vegetation structure, composition, and function in North American Arctic-Boreal ecosystems. We reviewed the ecosystem properties and scaling assumptions these models make, reviewed their applications from the scholarly literature, and conducted a survey of expert opinion to determine which processes are important but lacking in DVMs. We then grouped the models into four categories (specific intention models, forest species models, cohort models, and carbon tracking models) using cluster analysis to highlight similarities among the models. Our application review identified 48 papers that addressed vegetation dynamics either directly (22) or indirectly (26). The expert survey results indicated a large desire for increased representation of active layer depth and permafrost in future model development. Ultimately, this paper serves as a summary of DVM development and application in Arctic-Boreal environments and can be used as a guide for potential model users, thereby prioritizing options for model development. 

Human-conducted rating tasks are resource-intensive and demand significant time and financial commitments. As Large Language Models (LLMs) like GPT emerge and exhibit prowess across various domains, their potential in automating such evaluation tasks becomes evident. In this research, we leveraged four prominent LLMs: GPT-4, GPT-3.5, Vicuna, and PaLM 2, to scrutinize their aptitude in evaluating teacher-authored mathematical explanations. We utilized a detailed rubric that encompassed accuracy, explanation clarity, the correctness of mathematical notation, and the efficacy of problem-solving strategies. During our investigation, we unexpectedly discerned the influence of HTML formatting on these evaluations. Notably, GPT-4 consistently favored explanations formatted with HTML, whereas the other models displayed mixed inclinations. When gauging Inter-Rater Reliability (IRR) among these models, only Vicuna and PaLM 2 demonstrated high IRR using the conventional Cohen’s Kappa metric for explanations formatted with HTML. Intriguingly, when a more relaxed version of the metric was applied, all model pairings showcased robust agreement. These revelations not only underscore the potential of LLMs in providing feedback on student-generated content but also illuminate new avenues, such as reinforcement learning, which can harness the consistent feedback from these models.