Analyzing undergraduate students\' performance using educational data mining
Citations
180 citations
174 citations
117 citations
101 citations
95 citations
Cites background from "Analyzing undergraduate students\' ..."
...Educational data mining is a machine learning process that has been applied for studying and predicting student performance (Asif et al., 2017; Gasevic et al., 2014; Kostopoulos et al., 2018), for evaluating learning technologies integration process (Angeli et al....
[...]
...Educational data mining is a machine learning process that has been applied for studying and predicting student performance (Asif et al., 2017; Gasevic et al., 2014; Kostopoulos et al., 2018), for evaluating learning technologies integration process (Angeli et al., 2017), and for identifying…...
[...]
References
23,600 citations
2,466 citations
1,217 citations
864 citations
"Analyzing undergraduate students\' ..." refers background in this paper
...), years of enrolment, delayed courses, type of dedication (full-time, part-time), and debt situation; ElGamal (2013) predicts students' grades in a programming course by considering different factors like the students' mathematical background, programming aptitude, problem solving skills, gender, prior experience, high school mathematics grade, locality, previous computer programming experience, and e-learning usage; Huang and Fang (2013) predict course performance on the basis of students' performance in prerequisite courses and midterm examinations; Romero, Lopez, Luna, and Ventura (2013) investigated the appropriateness of quantitative, qualitative and social network information about forum usage as well as the appropriateness of classical classification algorithms and clustering algorithms to predict students' success or failure in a course; Arnold and Pistilli (2012) provide an early intervention solution for difficult courses based on students' activity in a Learning Management System. A number of studies predict students' passing/failing or overall academic achievement (total marks/CGPA) at the end of a degree programme; these studies are described in greater detail in the ‘Related work’ section. In clustering, the goal is to group objects into classes of similar objects. Though clustering has been used in educational data mining for a wide variety of tasks, an interesting sub-area is grouping students to study patterns of typical behaviours. The work by Cobo et al. (2012) finds typical behaviours in forums such as high-level workers, i.e. students that read all messages and post many messages in the forum, or lurkers, i.e. students who read all messages without posting any; Bower (2010) identifies groups of students with similar performance from Kindergarten till the end of high school; while Talavera and Gaudioso (2004) cluster students' interaction data to build profiles of students. Distillation of data for human judgment accords with what others call overview statistics and visualizations (Baker, 2010). Its aim is to help in understanding the results of analyses. For example, Elkina, Fortenbacher, and Merceron (2013) use an intuitive visualization of analytic results that provides insight about learning processes to teachers, E-learning providers and researchers....
[...]
...), years of enrolment, delayed courses, type of dedication (full-time, part-time), and debt situation; ElGamal (2013) predicts students' grades in a programming course by considering different factors like the students' mathematical background, programming aptitude, problem solving skills, gender, prior experience, high school mathematics grade, locality, previous computer programming experience, and e-learning usage; Huang and Fang (2013) predict course performance on the basis of students' performance in prerequisite courses and midterm examinations; Romero, Lopez, Luna, and Ventura (2013) investigated the appropriateness of quantitative, qualitative and social network information about forum usage as well as the appropriateness of classical classification algorithms and clustering algorithms to predict students' success or failure in a course; Arnold and Pistilli (2012) provide an early intervention solution for difficult courses based on students' activity in a Learning Management System....
[...]
...), years of enrolment, delayed courses, type of dedication (full-time, part-time), and debt situation; ElGamal (2013) predicts students' grades in a programming course by considering different factors like the students' mathematical background, programming aptitude, problem solving skills, gender, prior experience, high school mathematics grade, locality, previous computer programming experience, and e-learning usage; Huang and Fang (2013) predict course performance on the basis of students' performance in prerequisite courses and midterm examinations; Romero, Lopez, Luna, and Ventura (2013) investigated the appropriateness of quantitative, qualitative and social network information about forum usage as well as the appropriateness of classical classification algorithms and clustering algorithms to predict students' success or failure in a course; Arnold and Pistilli (2012) provide an early intervention solution for difficult courses based on students' activity in a Learning Management System. A number of studies predict students' passing/failing or overall academic achievement (total marks/CGPA) at the end of a degree programme; these studies are described in greater detail in the ‘Related work’ section. In clustering, the goal is to group objects into classes of similar objects. Though clustering has been used in educational data mining for a wide variety of tasks, an interesting sub-area is grouping students to study patterns of typical behaviours. The work by Cobo et al. (2012) finds typical behaviours in forums such as high-level workers, i.e. students that read all messages and post many messages in the forum, or lurkers, i.e. students who read all messages without posting any; Bower (2010) identifies groups of students with similar performance from Kindergarten till the end of high school; while Talavera and Gaudioso (2004) cluster students' interaction data to build profiles of students. Distillation of data for human judgment accords with what others call overview statistics and visualizations (Baker, 2010). Its aim is to help in understanding the results of analyses. For example, Elkina, Fortenbacher, and Merceron (2013) use an intuitive visualization of analytic results that provides insight about learning processes to teachers, E-learning providers and researchers. Bower's (2010) work combines dendrograms with heat map to provide an intuitive visualization of distinctive groups of students....
[...]
...), years of enrolment, delayed courses, type of dedication (full-time, part-time), and debt situation; ElGamal (2013) predicts students' grades in a programming course by considering different factors like the students' mathematical background, programming aptitude, problem solving skills, gender, prior experience, high school mathematics grade, locality, previous computer programming experience, and e-learning usage; Huang and Fang (2013) predict course performance on the basis of students' performance in prerequisite courses and midterm examinations; Romero, Lopez, Luna, and Ventura (2013) investigated the appropriateness of quantitative, qualitative and social network information about forum usage as well as the appropriateness of classical classification algorithms and clustering algorithms to predict students' success or failure in a course; Arnold and Pistilli (2012) provide an early intervention solution for difficult courses based on students' activity in a Learning Management System. A number of studies predict students' passing/failing or overall academic achievement (total marks/CGPA) at the end of a degree programme; these studies are described in greater detail in the ‘Related work’ section. In clustering, the goal is to group objects into classes of similar objects. Though clustering has been used in educational data mining for a wide variety of tasks, an interesting sub-area is grouping students to study patterns of typical behaviours. The work by Cobo et al. (2012) finds typical behaviours in forums such as high-level workers, i....
[...]
...), years of enrolment, delayed courses, type of dedication (full-time, part-time), and debt situation; ElGamal (2013) predicts students' grades in a programming course by considering different factors like the students' mathematical background, programming aptitude, problem solving skills, gender, prior experience, high school mathematics grade, locality, previous computer programming experience, and e-learning usage; Huang and Fang (2013) predict course performance on the basis of students' performance in prerequisite courses and midterm examinations; Romero, Lopez, Luna, and Ventura (2013) investigated the appropriateness of quantitative, qualitative and social network information about forum usage as well as the appropriateness of classical classification algorithms and clustering algorithms to predict students' success or failure in a course; Arnold and Pistilli (2012) provide an early intervention solution for difficult courses based on students' activity in a Learning Management System. A number of studies predict students' passing/failing or overall academic achievement (total marks/CGPA) at the end of a degree programme; these studies are described in greater detail in the ‘Related work’ section. In clustering, the goal is to group objects into classes of similar objects. Though clustering has been used in educational data mining for a wide variety of tasks, an interesting sub-area is grouping students to study patterns of typical behaviours. The work by Cobo et al. (2012) finds typical behaviours in forums such as high-level workers, i.e. students that read all messages and post many messages in the forum, or lurkers, i.e. students who read all messages without posting any; Bower (2010) identifies groups of students with similar performance from Kindergarten till the end of high school; while Talavera and Gaudioso (2004) cluster students' interaction data to build profiles of students....
[...]
485 citations