Abstract
Understanding the academic performance of students in colleges is an essential topic in Education research field. Educators, program coordinators and professors are interested in understanding how students are learning specific topics, how specific topics may influence the learning of other topics, how students’ grades/attendances in each course may represent important indicators to measure their performance, among other tasks. The use of data visualization and analytics is expanding in education institutions to perform a variety of tasks related to data processing and gaining into data-informed insights. In this paper, we present a visual analytic tool that combines data visualization and machine learning techniques to perform some visual analysis of students’ data from program courses. Two educational data collections were used to guide the creation of i) predictive models employing a variety of well known machine learning strategies, attempting to predict students’ future grade based on grade and attendance previous semesters and ii) a set interactive layouts that highlight the relationship between grades and attendance, also including additional variables such as gender, parents education level, among others. We performed several experiments, also using these data collections, to evaluate the layouts ability of highlighting interesting patterns, and we obtained promising results, demonstrating that such analysis may help the education experts to understand deficiencies on course structures.
Highlights
The importance of analytics and predictive methods in higher education, as well as the determining factors that contribute to academic performance are discussed in many research studies (Van Barneveld et al 2012; Mattingly et al 2012; Gutiérrez et al.) in order to improve the achievement of education goals, offer new modern opportunities for improving education system effectiveness and provide learning personalization
The impact of learning strategies and gender differences on academic performance are addressed by Ruffing et al (2015), the factors underlying the prediction of academic performance are still of great interest in educational psychology
We believe that a visual analysis tool employing machine learning and information visualization techniques improves the comprehension, by educational experts, of student’s behavior on subjects over the semesters, guiding them in defining effective strategies to mitigate related deficiencies
Summary
The importance of analytics and predictive methods in higher education, as well as the determining factors that contribute to academic performance are discussed in many research studies (Van Barneveld et al 2012; Mattingly et al 2012; Gutiérrez et al.) in order to improve the achievement of education goals, offer new modern opportunities for improving education system effectiveness and provide learning personalization. the impact of learning strategies and gender differences on academic performance are addressed by Ruffing et al (2015), the factors underlying the prediction of academic performance are still of great interest in educational psychology. One reliable task is to ask the school for some anonymized information about previous students to obtain useful information to perform analytic tasks. In this sense, Etemadpour et al Smart Learning Environments (2020) 7:2 novel analysis strategies are useful in comprehending educational scenarios involving students performance and related factors, guiding decision making by educational experts. We believe that a visual analysis tool employing machine learning and information visualization techniques improves the comprehension, by educational experts, of student’s behavior on subjects over the semesters, guiding them in defining effective strategies to mitigate related deficiencies. Our main goal is to investigate the ability of the system’s tools in addressing the following research questions:
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.
