What Satisfies Students? Mining Student-Opinion Data with Regression and Decision Tree Analysis

Thomas, Emily; Galambos, Nora

doi:10.1023/b:rihe.0000019589.79439.6e

Cited by 208 publications

(158 citation statements)

References 22 publications

Supporting

Mentioning

140

Contrasting

Unclassified

Order By: Relevance

“…Thomas and Galambos [42] argue that the utilization of data mining techniques in higher education research has been insufficient. Sharma and Singh [38] emphasize important issues currently facing educational system (high dropout rates, personalization of teaching, etc.)…”

Section: Review Of Previous Researchmentioning

confidence: 99%

Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

Babić

2015

Croat. Oper. Res. Rev.

View full text Add to dashboard Cite

Abstract. Student satisfaction with courses in academic institutions is an important issue and is recognized as a form of support in ensuring effective and quality education, as well as enhancing student course experience. This paper investigates whether there is a connection between student satisfaction with courses and log data on student courses in a virtual learning environment. Furthermore, it explores whether a successful classification model for predicting student satisfaction with course can be developed based on course log data and compares the results obtained from implemented methods. The research was conducted at the Faculty of Education in Osijek and included analysis of log data and course satisfaction on a sample of third and fourth year students. Multilayer Perceptron (MLP) with different activation functions and Radial Basis Function (RBF) neural networks as well as classification tree models were developed, trained and tested in order to classify students into one of two categories of course satisfaction. Type I and type II errors, and input variable importance were used for model comparison and classification accuracy.The results indicate that a successful classification model using tested methods can be created. The MLP model provides the highest average classification accuracy and the lowest preference in misclassification of students with a low level of course satisfaction, although a t-test for the difference in proportions showed that the difference in performance between the compared models is not statistically significant. Student involvement in forum discussions is recognized as a valuable predictor of student satisfaction with courses in all observed models.

show abstract

Section: Review Of Previous Researchmentioning

confidence: 99%

Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

Babić

2015

Croat. Oper. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…They reported that k-nearest neighbors obtained the best results, with 82.3% accuracy; however, decision trees also performed well. Thomas and Galambos (2004) used regression analysis and decision trees with the CHAID (CHi-squared Automatic Interaction Detection) algorithm to identify the academic satisfaction of students in three major aspects: academic experiences, social integration and campus services-facilities. The results obtained using the decision tree analysis revealed that social integration is a determining factor for students' satisfaction, particularly for students who are less academically engaged.…”

Section: Knowledge Discovery In Databasesmentioning

confidence: 99%

Brief Review of Educational Applications Using Data Mining and Machine Learning

Nájera

Calleja

2017

REDIE

View full text Add to dashboard Cite

The large amounts of data used nowadays have motivated research and development in different disciplines in order to extract useful information with a view to analyzing it to solve difficult problems. Data mining and machine learning are two computing disciplines that enable analysis of huge data sets in an automated manner. In this paper, we give an overview of several applications using these disciplines in education, particularly those that use some of the most successful methods in the machine learning community, such as artificial neural networks, decision trees, Bayesian learning and instance-based methods. Although these two areas of artificial intelligence have been applied in many real-world problems in different fields, such as astronomy, medicine, and robotics, their application in education is relatively new. The search was performed mainly on databases such as EBSCO, Elsevier, Google Scholar, IEEEXplore and ACM. We hope to provide a useful resource for the education community by presenting this review of approaches.Keywords: Education, Data mining, Machine learning. ResumenLa gran cantidad de datos utilizados en la actualidad han motivado la investigación y el desarrollo en diferentes disciplinas buscando extraer información útil con el fin de analizarla para resolver problemas difíciles. La Minería de datos y el Aprendizaje automático son dos disciplinas informáticas que permiten analizar enormes conjuntos de datos de forma automática. En este documento proporcionamos un panorama de varias aplicaciones que utilizan estas disciplinas en la Educación, particularmente aquellas que utilizan algunos de los métodos más exitosos en la comunidad de aprendizaje automático, como redes neuronales artificiales, árboles de decisión, aprendizaje bayesiano y métodos basados en instancias. Aunque estas dos áreas de la inteligencia artificial se han aplicado en muchos problemas del mundo real en diferentes campos, como la Astronomía, la Medicina y la Robótica, su aplicación en la Educación es relativamente nueva. La búsqueda se realizó principalmente en bases de datos como EBSCO, Elsevier, Brief review of educational applications using data mining and machine learning Google Scholar, IEEEXplore y ACM. Esperamos proporcionar un recurso útil para la comunidad educativa con esta revisión de enfoques.Palabras clave: Educación, Minería de datos, Aprendizaje automático.

show abstract

“…Stepwise linear regression was used for predicting student academic performance [34] while multiple linear regression was used for predicting time to be spent on a learning page [35]. [36] identified variables that could predict success in college courses using multiple regression while [37], used regression and decision trees analysis for predicting university students" satisfaction. Linear regression was used for predicting exam results in distance education courses [38], for predicting end-of-year accountability assessment scores [39] and also for predicting the probability that the student"s next response is correct [40].…”

Section: Overview Of Literaturementioning

confidence: 99%

Predicting Students’ Academic Performances – A Learning Analytics Approach using Multiple Linear Regression

Oyerinde¹,

Chia²

2017

IJCA

View full text Add to dashboard Cite

Learning Analytics is an area of Information Systems research that integrates data analytics and data mining techniques with the aim of enhancing knowledge management and learning delivery in education management..The current research proposes a framework to administer prediction of Students Academic Performance using Learning Analytics techniques. The research illustrates how this model is used effectively on secondary data collected from the Department of Computer Science, University of Jos, Nigeria.Multiple Linear Regression was used with the aid of the Statistical Package for Social Sciences (SPSS) analysis tool. Statistical Hypothesis testing was then used to validate the model with a 5% level of significance.

show abstract

What Satisfies Students? Mining Student-Opinion Data with Regression and Decision Tree Analysis

Cited by 208 publications

References 22 publications

Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

Brief Review of Educational Applications Using Data Mining and Machine Learning

Predicting Students’ Academic Performances – A Learning Analytics Approach using Multiple Linear Regression

Contact Info

Product

Resources

About