| Title |
Analysis of Student Achievement Scores: A Machine Learning Approach |
| Authors |
García-Torres M. , BECERRA ALONSO, DAVID, Gómez-Vela F.A. , Divina F. , LÓPEZ COBO, ISABEL, Martínez-Álvarez F. |
| External publication |
No |
| Means |
Advances in Intelligent Systems and Computing |
| Scope |
Conference Paper |
| Nature |
Científica |
| Web |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065711807&doi=10.1007%2f978-3-030-20005-3_28&partnerID=40&md5=f6411513fcec608eea3d839dbcccb3ce |
| Publication date |
01/01/2020 |
| Scopus Id |
2-s2.0-85065711807 |
| DOI |
10.1007/978-3-030-20005-3_28 |
| Abstract |
Educational Data Mining (EDM) is an emerging discipline of increasing interest due to several factors, such as the adoption of learning management systems in education environment. In this work we analyze the predictive power of continuous evaluation activities with respect the overall student performance in physics course at Universidad Loyola Andalucíıa, in Seville, Spain. Such data was collected during the fall semester of 2018 and we applied several classification algorithms, as well as feature selection strategies. Results suggest that several activities are not really relevant and, so, machine learning techniques may be helpful to design new relevant and non-redundant activities for enhancing student knowledge acquisition in physics course. These results may be extrapolated to other courses. © 2020, Springer Nature Switzerland AG. |
| Keywords |
Classification (of information); Curricula; Data mining; Feature extraction; Information management; Information systems; Information use; Machine learning; Management information systems; Classification algorithm; Educational data mining; Educational data minings (EDM); Evaluation activity; Learning management system; Machine learning approaches; Machine learning techniques; Student achievement; Students |
| Universidad Loyola members |
|
Manage cookies