Article Preview
TopIntroduction
The recent Researches predict the student difficulties (Maheshwari, et al., 2020; Chui, et al., 2020), the student achievements (Lerche and Kiel, 2018) and academic performance (Son and Fujita, 2019; Tomasevic, et al., 2020; Waheed et, al., 2020), which aim to empower learning practices design (Galloway, et al., 2020; Goodyear, 2020) and learning environment effectiveness (Quinn and Gray, 2019; Dyrbye, et al., 2020; Asarta and Schmidt, 2020). This emerging landscape have emerged especially in higher education (Viberg, et al., 2018) to improve and support the learning process and provide feedbacks for educators and education decision makers. The main addressed problem is whether the data analytics sciences can be applied to the learning field and can be deployed widely into educational institutions.
The instructors and decision makers are increasingly interested in modern learning analytics techniques, which provide accurate predictions for student achievements. These learning analytics techniques are based on educational data and data mining to provide a comprehensive analysis and optimization of the learning experience.
In the literature, learning analytics refer to a mean to help educators and learning environments (Christensen, et al., 2018; Christensen et al., 2019) using collection and analysis of learners’ data for the main goal of understanding and optimizing the learning process and outcomes (Viberg, et al., 2018). Further goals support the learning design and regulation of learning by offering a dashboard that provides needed feedback for learner and instructors (Sedrakyan, et al., 2020). The aim of advanced learning analytics research studies is to offer a personalized learning approaches (Tsai, et al., 2020) and analyze factors influencing learners’ achievements (Moreno-Marcos, et al., 2020).
Especially, developing an educational warning system (Zhang, et al., 2020; Du, et al., 2020) to predict academic performance, dropping-out, failure and advanced education indicators has great interest. Many researchers have addressed the students retention and students at-risk. These two parameters are narrowly related especially in the first year in higher education. Universities reports demonstrated that more than 37% of students leave the educational institution in the first or second year for four-year institutions (ACT Institutional Data File, 2018). This highlighted the importance of prediction student at risk in the enrolled courses during the first year to establish suitable action plan learning practices review and updates.