1 / 22

Pei-Yu Wang

Using collaborative filtering to support college students ’ use of online forum for English learning. Pei-Yu Wang. Reporter :黃詩哲. Outline. 1 .Introduction 2.Method 3.Conclusion. Introduction(1/4). Collaborative filtering Books Movies News articles. Introduction(2/4 ).

dorit
Download Presentation

Pei-Yu Wang

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. Using collaborative filtering to support college students’ use of online forum for English learning Pei-Yu Wang Reporter:黃詩哲

  2. Outline 1.Introduction 2.Method 3.Conclusion

  3. Introduction(1/4) • Collaborative filtering • Books • Movies • News articles

  4. Introduction(2/4) • Proliferation of information • Information overload

  5. Introduction(3/4) • Does the recommender improve students’ use of online forums for English learning? • Is there any difference in online behaviors between students who use a traditional forum and students who usea forum with a recommender?

  6. Introduction(4/4) • Is there any difference in learning motivation between students who usea traditional forum and students who use a forum with a recommender? • Is there any difference in learningachievement between students who use a traditional forum and students who use a forum with a recommender?

  7. Method(1/15) • Open-source softwareDrupal • PHP • Account registration • Maintenance • Menu management • RSS • Page layout

  8. Method(2/15) • Top-N nearest neighbors • Users who browsed this node also browsed. • Recommended for you.

  9. Method(3/15)

  10. Method(4/15) • Participants • One hundred and forty-two freshman(n=142) • Experimental group(n=72) • Control group(n=70)

  11. Method(5/15) • Data collection • Pre-test • Midterm exam • Final exam • Online survey • Weblog data

  12. Method(6/15) • Comparison of mean posting frequency for each student

  13. Method(7/15) • Comparison of mean replying frequency for each student.

  14. Method(8/15) • Comparison of mean reading frequency for each post.

  15. Method(9/15) • Comparison of student achievement performance.

  16. Method(10/15) • Descriptive statistics for student perception to the recommender.

  17. Method(11/15) • Open-ended response for student perception to the recommender.

  18. Method(12/15) • Open-ended response for student perception to the recommender.

  19. Method(13/15) • The recommender can be more personalized. For example, the recommender can let users set up their own criteria to rate articles. • The rating system could use stars (from one to five) or thumb-up icons to display the recommended posts.

  20. Method(14/15) • Creating an explicit rating function to each post would improve utility. For example, students or instructors can vote or mark articles good in their opinion. • Connecting the recommended posts to Facebook was also suggested.

  21. Method(15/15) • The instructor should present or discuss recommended articles in class to enhance student use of the forum.

  22. Conclusion • Significantly enhance students’ reading frequency of forum articles. • Improve students’ summary writing ability. • This research was conducted in a shorteight week period.

More Related