Khoudi, Zakaria and Nachaoui, Mourad and Lyaqini, Soufiane (2024) Finding the contextual impacts on Students’ Mathematical performance using a Machine Learning-based Approach. INFOCOMMUNICATIONS JOURNAL : A PUBLICATION OF THE SCIENTIFIC ASSOCIATION FOR INFOCOMMUNICATIONS (HTE), 16 (SI). pp. 12-21. ISSN 2061-2079
|
Text
InfocomJournal_2024_SpecISS_CogInf_CogAspVR_2.pdf Download (7MB) | Preview |
Abstract
An extensive dataset for examining Moroccan eighth-grade pupils’ mathematical prowess was made available by the 2019 Trends in Mathematics and Science Study (TIMSS). The TIMSS 2019 public dataset contained 8390 Moroccan stu- dents, who were the subject of this research. Based on how well they could solve mathematical problems, the participants were split into 3108 high achievers and 5282 poor achievers in the mathematics phase of the exam. This study aimed to pinpoint the essential environmental elements affecting eighth-grade pupils’ mathematical abilities. In order to do this, the research used cutting-edge machine learning methods, particularly the efficient distributed gradient boosting toolkit XGBoost. From a vast collection of 700 possible components, this strategy proved critical in identifying the most relevant variables. These factors included a broad spectrum of components at the student, teach er, and school levels. After a thorough investigation, 12 critical contextual factors distinguishing between arithmetic prodigies and average performers were successfully found. The discov ery of these critical characteristics has significant implications for future instructional efforts, especially in improving high school pupils’ mathematical proficiency. Knowledge of these factors may assist educators and policymakers in creating fo cused interventions and pedagogical approaches that enhance mathematics performance and comprehension. This research emphasizes how complex mathematics accomplishment is and how crucial it is to approach educational planning holistically. Identifying and addressing these critical environmental ele ments can significantly enhance students’ mathematics achieve ments at a crucial juncture in their academic development.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Contextual factors, Machine learning, Mathematics performance, Moroccan students, TIMSS 2019 |
Subjects: | Q Science / természettudomány > QA Mathematics / matematika |
Depositing User: | Andrea Tankó |
Date Deposited: | 01 Aug 2024 13:24 |
Last Modified: | 01 Aug 2024 13:24 |
URI: | https://real.mtak.hu/id/eprint/201559 |
Actions (login required)
![]() |
Edit Item |