Designing a Course Recommendation System on Web based on the Students - PowerPoint PPT Presentation

About This Presentation
Title:

Designing a Course Recommendation System on Web based on the Students

Description:

Title: PowerPoint Presentation Last modified by: sharon Created Date: 1/1/1601 12:00:00 AM Document presentation format: Other titles – PowerPoint PPT presentation

Number of Views:35
Avg rating:3.0/5.0
Slides: 9
Provided by: pittEdu7
Learn more at: https://sites.pitt.edu
Category:

less

Transcript and Presenter's Notes

Title: Designing a Course Recommendation System on Web based on the Students


1
Designing a Course Recommendation System on Web
based on the Students course Selection Records
  • Ko-Kang Chu, Maiga Chang and Yen-The Hsia
  • (Dept. of Information and Computer Engineering,
    Chung-Yuan Christian Univ. Taiwan)

Presented by Sharon HSIAO Jan.2007
2
agenda
  • Introduction
  • Prediction methodology Recommendation Process
  • Results Evaluation
  • Proposed Future Research

3
introduction
  • Focus on relation between course categories and
    students preferences
  • Preference Mandatory courses should not be taken
    into consideration when analyzing students
    preference
  • Category Classify coursesgtgtEach course covers
    more than one categorygtgtweigh courses
  • Fuzzy AI(90),Research(85),Math(70)
  • Neural Networks AI(90),Research(85),Math(70)
  • Ken Fuzzy and Neural Networks
  • Objective construct a web-based course
    recommendation system that only depends on the
    courses chosen by students

4
Prediction methodology
  • Datamining technique
  • Apriori algorism (Agrawal Srikant, 1994)

5
Recommendation process
Classifying courses/designing weights
Collecting Students Course Selection Records
Make Suggestions to Student
6
Results and Evaluation
  • 4 consecutive terms, senior college students
  • Class 2001 127 students course selection
    record, 34/83 questionnaires response
  • Class 2002 102, 100 response rate
  • 6 categories research, theory, math, hardware,
    software, network (information science)

7
Accuracy rate for preference sequence
  • General assumption 4th term should have the
    highest accuracy rate
  • Explanation fewer prerequisites, more electives,
    tend to follow graduate school guidance
  • Class 2002 target 13 students who plan to go to
    graduate school straight after college

8
Proposed Future Research
  • Students needs change analysis
  • How to find course categories classified by
    students? What are the relations among courses in
    students mind?
  • Time series analysis
  • Is it possible to develop or plan a series of
    courses depends on the students major interests?
Write a Comment
User Comments (0)
About PowerShow.com