Design of a Course Recommender System as an Application of Collecting Graduating AttributesReportar como inadecuado




Design of a Course Recommender System as an Application of Collecting Graduating Attributes - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Graduating Attributes, Recommender Systems

Bakhshinategh, Behdad

Supervisor and department: ZAIANE, Osmar Computing Science ElAtia, Samira Education

Examining committee member and department: Buro, Michael Computing Science Kanuka, Heather Education

Department: Department of Computing Science

Specialization:

Date accepted: 2016-09-26T13:09:16Z

Graduation date: 2016-06:Fall 2016

Degree: Master of Science

Degree level: Master's

Abstract: In educational research, the term of Graduating Attributes has been used for the qualities, skills and understandings a university community agrees its students would develop. Having a description of Graduating Attributes is one of the ways through which universities can display the outcomes of higher education. But can Graduating Attributes be used also to enhance the process of learning? In this thesis, we discuss how graduating attributes can be used in data mining applications to improve the learning process. An example of a data mining application can be a course recommender system which helps students to choose the courses they would participate in. In our work we have implemented this recommender system as an example of possible applications which Graduating Attributes can provide. In order to achieve such a goal we first needed to implement a tool for assessing Graduating Attributes and gather data. In spite of implementing this tool, we were not able to gather sufficient amount of data. As a result, based on the structure of data in our assessment tool, we have generated synthetic data which we have used for the evaluation of the course recommender system. The results of the recommendation improve over time as a result of having more data. The mean squared error decreases from 0.32 in second semester to 0.08 in the tenth semester.

Language: English

DOI: doi:10.7939-R3C824R28

Rights: This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for the purpose of private, scholarly or scientific research. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.





Autor: Bakhshinategh, Behdad

Fuente: https://era.library.ualberta.ca/


Introducción



Design of a Course Recommender System as an Application of Collecting Graduating Attributes by Behdad Bakhshinategh A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science Department of Computing Science University of Alberta c Behdad Bakhshinategh, 2016 Abstract In educational research, the term of Graduating Attributes has been used for the qualities, skills and understandings a university community agrees its students would develop.
Having a description of Graduating Attributes is one of the ways through which universities can display the outcomes of higher education.
But can Graduating Attributes be used also to enhance the process of learning? In this thesis, we discuss how graduating attributes can be used in data mining applications to improve the learning process.
An example of a data mining application can be a course recommender system which helps students to choose the courses they would participate in.
In our work we have implemented this recommender system as an example of possible applications which Graduating Attributes can provide.
In order to achieve such a goal we first needed to implement a tool for assessing Graduating Attributes and gather data.
In spite of implementing this tool, we were not able to gather sufficient amount of data.
As a result, based on the structure of data in our assessment tool, we have generated synthetic data which we have used for the evaluation of the course recommender system.
The results of the recommendation improve over time as a result of having more data.
The mean squared error decreases from 0.32 in second semester to 0.08 in the tenth semester. ii To the Count For teaching me everything I need to know about math. iii The good news about computers is that they do what you tell them to do. The bad news is that they do what you tell them to do. – Ted Nelson iv Table of Contents 1 Introduction 1.1 Thesis Statement ....





Documentos relacionados