Finding the Best Algorithms and Effective Factors in Classification of Turkish Science Student Success

Abstract

Educational Data Mining (EDM) is an important tool in the field of classification of educational data that helps researchers and education planners analyse and model available educational data for specific needs such as developing educational strategies. Trends International Mathematics and Science Study (TIMSS) which is a notable study in educational area was used in this research. EDM methodology was applied to the results of TIMSS 2015 that presents data culled from eighth grade students from Turkey. The main purposes are to find the algorithms that are most appropriate for classifying the successes of students, especially in science subjects, and ascertaining the factors that lead to this success. It was found that logistic regression and support vector machines – poly kernel are the most suitable algorithms. A diverse set of features obtained by feature selection methods are “Computer Tablet Shared”, “Extra Lessons Last 12 Month”, “Extra Lessons How Many Month”, “How Far in Education Do You Expect to Go”, “Home Educational Resources”, and “Student Confident in Science” and these features are the most effective features in science success. Keywords: classification algorithms, educational data mining, eighth grade, science success, TIMSS 2015.

Cross-National Comparisons of Students’ Science Success Based on Gender Variability: Evidence From Timss

“…These findings are consistent with previous studies which have been pointed out that students with lower educational expectations, lower educational resources or lower confidence tend to be less successful than their peers with higher expectations, resources or confidence (e.g. Bouhlila, 2011;Filiz & Öz, 2019;Hammori, 2004;Liu & Meng, 2010;Ogura, 2006;Ramirez, 2006;Topçu, Erbilgin, & Arıkan, 2016). The education system, which focuses on the following issues, might make a significant progress in achieving success: (1) improving efforts to increase students' confidence in science;…”

Educational Data Mining for Student Performance Prediction: A Systematic Literature Review (2015-2021)

“…For RQ1, the two main categories of the research focus are identifying aspects that influence student performance and examining DM algorithms performance. These two categories are often discussed in educational prediction studies in which DM was employed to determine factors that affect student performance and the performance of algorithms used were examined [34]. The findings are consistent with Shin and Shim's research [35].…”

Which noncognitive features provide more information about reading performance? A data-mining approach to big educational data

“…Although SES is not the only variable affecting academic achievement (Caldwell & Ginther, 1996; Milne & Plourde, 2006), it is one of the necessary prerequisites for success (Koyuncu & Fırat, 2020; Reardon, 2016). As a matter of fact, the availability of a child's own room, work desk, supporting materials (e.g., books, dictionaries, educational software), and technical support (e.g., ruler, miter, computer) are the basic elements for effective study (Filiz & Öz, 2019).…”