Learning Analytics and Computerized Formative Assessments: An Application of Dijkstra’s Shortest Path Algorithm for Personalized Test Scheduling

Abstract

The use of computerized formative assessments in K–12 classrooms has yielded valuable data that can be utilized by learning analytics (LA) systems to produce actionable insights for teachers and other school-based professionals. For example, LA systems utilizing computerized formative assessments can be used for monitoring students’ progress in reading and identifying struggling readers. Using such LA systems, teachers can also determine whether progress is adequate as the student works towards their instructional goal. However, due to the lack of guidelines on the timing, number, and frequency of computerized formative assessments, teachers often follow a one-size-fits-all approach by testing all students together on pre-determined dates. This approach leads to a rigid test scheduling that ignores the pace at which students improve their reading skills. In some cases, the consequence is testing that yields little to no useful data, while increasing the amount of instructional time that students miss. In this study, we propose an intelligent recommender system (IRS) based on Dijkstra’s shortest path algorithm that can produce an optimal assessment schedule for each student based on their reading progress throughout the school year. We demonstrated the feasibility of the IRS using real data from a large sample of students in grade two (n = 668,324) and grade four (n = 727,147) who participated in a series of computerized reading assessments. Also, we conducted a Monte Carlo simulation study to evaluate the performance of the IRS in the presence of unusual growth trajectories in reading (e.g., negative growth, no growth, and plateau). Our results showed that the IRS could reduce the number of test administrations required at both grade levels by eliminating test administrations in which students’ reading growth did not change substantially. In addition, the simulation results indicated that the IRS could yield robust results with meaningful recommendations under relatively extreme growth trajectories. Implications for the use of recommender systems in K–12 education and recommendations for future research are discussed.

Chinese university students’ conceptions of feedback and the relationships with self-regulated learning, self-efficacy, and English language achievement

“…Given this situation, the Chinese Ministry of Education recently initiated a series of educational reforms to facilitate learning, and quality assessment is one of these reforming targets (Chinese Ministry of Education, 2004Education, , 2007. Formative assessment is advocated in higher education in China, for it measures students' progress as a process instead of an outcome (Bulut et al, 2022). Feedback, as an integrated part of formative assessment, takes up the largest proportion of the College English classroom assessment in China (Jin, 2020).…”

Sound-Based Localization Using LSTM Networks for Visually Impaired Navigation

“…This algorithm is used to calculate the shortest distance between two points (shortest path first, SPF) [29,30]. The coordinate path is saved in matrix form.…”

Optimized Screening for At-Risk Students in Mathematics: A Machine Learning Approach

“…Fourth, depending on the outcomes of the screening procedure, students could be more or less frequently tested based on their academic growth in mathematics throughout the academic year. Previous research showed that students' assessment schedules can be personalized in core subject areas based on their learning progress estimated from Star assessment scores [46][47][48]. Future research can investigate the relationship between screening results and students' academic growth throughout the academic year by following a personalized assessment schedule for students.…”