1 / 8

Designing a Course Recommendation System on Web based on the Students’ course Selection Records

This study focuses on developing a web-based course recommendation system by analyzing students' course preferences and categories. The methodology includes data mining techniques, classification of courses, and evaluating the accuracy of the recommendation process based on student records.

besparza
Download Presentation

Designing a Course Recommendation System on Web based on the Students’ course Selection Records

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  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 student’s preferences • Preference: Mandatory courses should not be taken into consideration when analyzing students preference • Category: Classify courses>>Each course covers more than one category>>weigh 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. Construct Important Orders of Categories Merge Rules into A Preference Sequence 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 • Student’s needs change analysis • How to find course categories classified by students? What are the relations among courses in student’s mind? • Time series analysis • Is it possible to develop or plan a series of courses depends on the student’s major interests?

More Related