Abstract
In the literature related to higher education, the concept of dropout has been approached from several perspectives and, over the years, its definition has been influenced by the use of diversified semantic interpretations. In a general higher education environment dropout can be broadly characterized as the act of a student engaged in a course leaving the educational institution without finishing the course. This paper describes the proposal of the architecture of a computational system, PDE (Predicting Dropout Events), based on machine learning (ML) algorithms and specifically designed for predicting dropout events in a higher level educational environment. PDE’s main subsystem implements a group of instance-based learning (IBL) algorithms which, taking into account a particular university-course environment, and based on log files containing descriptions of previous dropouts events, is capable to predict when a student already engaged in the course, is prone to dropout, so preventive measures could be quickly implemented.
Highlights
In educational environments related to traditional learning or e-learning, the dropout problem has been recurrent for many years already and, so far, it has shown to be a difficult problem to be solved, even when both, the administrative staff and the educational staff are heavily engaged in its solution
This paper describes the proposal of the architecture of a computational system, PDE (Predicting Dropout Events), based on machine learning (ML) algorithms and designed for predicting dropout events in a higher level educational environment
The difficulties to successfully address the problem are mainly due to its many dimensions, such as: the need for correctly detecting the relevant variables involved in the process and how they relate to each other; the volatility of many of the variables involved; the influences of the social environment that embeds the educational environment; the influences of the internal social environment, that is an inherent part of the educational system, etc
Summary
In educational environments related to traditional learning or e-learning, the dropout problem has been recurrent for many years already and, so far, it has shown to be a difficult problem to be solved, even when both, the administrative staff and the educational staff are heavily engaged in its solution. Subprocesses and interrelationships are highly volatile over time, reflecting the dynamics of current educational environments In such scenario, the only way of monitoring the dynamics of dropout processes, aiming at preventing them, is through a computational system capable to detect patterns of student‟s behavior that may lead to a dropout decision.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
