Learning analytics in programming courses: Review and implications

The adoption and use of learning analytics tools to improve decision making in higher learning institutions: An extension of technology acceptance model

“…With the advancement of technology, there are more opportunities to enhance the learning and teaching experience for students and instructors and provide more personalized education [ 2 , 5 ]. LATs is one such technology whose use has been found to be beneficial in the field of education, particularly in higher education [ 4 , [110] , [111] , [112] ]. This research primarily aimed to develop and propose a LAT adoption model for HLIs that contains the factors that influence LAT adoption within the institutions.…”

“…More specifically, Learning Analytics Tools (LATs) are described as distinct applications and software programs utilized for collecting, analyzing, and reporting data for learning. They are educational tools that are useful for students, teachers, and the overall learning institution [ [1] , [2] , [3] , [4] , [5] , [6] ].…”

Reproducing Predictive Learning Analytics in CS1

“…Similarly, Castro-Wunsch and colleagues (2017) reproduced a method for identifying at-risk students in a different course and extended the analysis by assessing the efficacy of neural networks in predicting these students. Notably, while reproduction studies are conducted in CSE research, they are still quite scarce (Omer et al, 2023), despite their value in improving the validity of predictive learning analytics methods. Indeed, while the merit of reproduction studies is recognized, conducting them is challenging.…”

“…For example, grade expectations reported at the beginning of a CS1 course strongly indicate course achievement (Rountree et al, 2002). In practice, learning analytics research has to draw information from multiple sources, such as clickstreams, trace logs, interviews, observations, and demographic details, to fully understand students' metacognitive and self-regulation processes and their effect on achievement (Omer et al, 2023). When planning interventions and feedback systems with learning analytics, it's imperative to factor in students' individual attributes, such as self-efficacy and academic experiences (see Dawson et al, 2017).…”