scholarly journals A survey on educational data mining methods used for predicting students' performance

2021 ◽  
Author(s):  
Wen Xiao ◽  
Ping Ji ◽  
Juan Hu
Keyword(s):  
Data Mining ◽  
Educational Data Mining ◽  
Mining Methods

Using Big Data to Improve the Educational Infrastructure and Learning Paradigm

2016 ◽  
pp. 158-181 ◽  
Author(s):  
Areej Fatemah Meghji ◽  
Naeem A. Mahoto
Keyword(s):  
Data Mining ◽  
Big Data ◽  
Student Behavior ◽  
Learning Experience ◽  
Educational Data Mining ◽  
Generic Model ◽  
Gold Mine ◽  
Information Retention ◽  
Pedagogical Decisions ◽  
Mining Methods

In higher education, the demand for improved information in relation to educational and learning outcomes is greater than ever before. Leveraging technology, new models of education have emerged that are not only improving modes of lecture delivery and information retention, but also generating huge amounts of data. This data is potentially a gold mine that needs to be explored to uncover patterns associated with student behavior and how information is processed, retained and used by the students. This chapter proposes a generic model that uses the techniques of educational data mining to explore and analyze Big Data being generated by the education sector. This chapter also examines the various questions that can be answered using educational data mining methods and how the discovered patterns can be used to enrich the learning experience of a student as well as help teachers make pedagogical decisions.

scholarly journals Resource description framework based methodology to personalise learning

2016 ◽  
Vol 57 ◽  
Author(s):  
Irina Krikun ◽  
Eugenijus Kurilovas
Keyword(s):  
Systematic Review ◽  
Data Mining ◽  
Learning Analytics ◽  
Educational Data Mining ◽  
Educational Management ◽  
Review Analysis ◽  
Mining Methods ◽  
Description Framework ◽  
Trained Teachers ◽  
Resource Description

The paper aims to analyse Educational Data Mining/Learning Analytics application trends to personalise learning. First of all, systematic literature review was performed. Based on the systematic review analysis, the main trends on applying educational data mining methods to personalise learning were identified. Second, three main tendencies on educational data mining/learning analytics application in education were formulated. They are: (a) Educational Data Mining/Learning Analytics support self-directed autonomous learning; (b) Educational Data Mining/Learning Analytics systems become essential tools of educational management; and (c) most teaching is delegated to computers, and Educational Data Mining/Learning Analytics based recommendations become better and more reliable than those that can be produced by even the best-trained teachers.

scholarly journals Educational data mining: overview and research trends

2015 ◽  
Vol 56 ◽  
Author(s):  
Dovilė Stumbrienė ◽  
Audronė Jakaitienė
Keyword(s):  
Data Mining ◽  
Web Of Science ◽  
Contextual Information ◽  
Educational Data Mining ◽  
Research Trends ◽  
Data Sources ◽  
Classification Methods ◽  
International Database ◽  
Information Classification ◽  
Mining Methods

The article presents a systematic literature review about the most commonly used data sources and data mining methods in education. International database Web of Science was selected. Excluding short conference proceedings and articles without empirical data, 14 papers were analyzed in detail. It was obtained that the most explored databases of learners consisted of subjects evaluation results together with contextual information. Classification methods were the most commonly used; to a lesser extent regression analysis and clustering. An educational data mining research overview in Lithuania ends the article.

scholarly journals An inclusive survey of students performance with various data mining methods

2018 ◽  
Vol 7 (3.3) ◽  
pp. 522
Author(s):  
A S. Arunachalam ◽  
K Rajeswari
Keyword(s):  
Data Mining ◽  
Educational Data Mining ◽  
Efficient Technique ◽  
Educational Institutions ◽  
Survey Paper ◽  
Academic Level ◽  
Current Technique ◽  
Student’S Performance ◽  
Mining Methods ◽  
Tools And Techniques

Educational institutions are the source of generating quality students in order to make them do better service for the nation. It is a must for all educational institutions to be aware of the competency and academic level of every student so as to study their performance. The key attributes to identify the performance are to have controlled parameter with clear data. So it is important to set the standards and calibration measures in order to make the study of students’ performance an efficient one. There are several tools and techniques available to perform this prediction study. Among all, Data mining is the best and the most efficient technique to handle prediction process. Among data mining, EDM (Educational Data Mining) is much more popular in the present century and hence it is beneficial to make a research on the current technique. This survey paper focuses on various Data Mining approaches in order to forecast student’s performance and bring clarity in students’ results and faculty’s contribution as a success.  

Sign in / Sign up

Export Citation Format

Share Document