Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Deloping the Ultimate Course Search Tool to Increase Retention and Learning

862 views

Published on

This PowerPoint was presented at the Emerging Learning Design 2014 Conference. We discuss the NSF funded iSECURE project and beta testing preliminary data. Slides of the tool are included.

Published in: Education
  • Be the first to comment

  • Be the first to like this

Deloping the Ultimate Course Search Tool to Increase Retention and Learning

  1. 1. Developing the Ultimate Course Search Tool to Increase Retention and Learning Edina Renfro-Michel, Ph.D., LPC, ACS renfromichee@mail.montclair.edu Sailume Walo, MA, LPC waloroberts1@mail.montclair.edu Montclair State University Vincent Oria, Ph.D. New Jersey Institute of Technology vincent.oria@njit.edu
  2. 2. Agenda • Millennials! • Our NSF Grant • UCS and Learning Preferences • What We Have Done and Are Doing • In the Future…. • Implications for Higher Education • The Tool!
  3. 3. Millennials • Multitask • Have Short Attention Spans • Tend to be Visual Learners • Bore Easily • Want Instant Gratification • Want Control Over Their Learning • Have an Expectation to Achieve • Lack Self-Reflection Skills • Need Individualized Educational Opportunities
  4. 4. Our NSF Grant - iSECURE •Ultimate Course Search (UCS) • Use all digital Material • Textbook • Articles, PowerPoint Presentations, etc. • Lecture Videos • Create Searches • Integrate Learning Preferences
  5. 5. iSECURE • Multimedia data often relies on annotation However, manual annotation is tedious • How to effectively and efficiently search such a huge amount of heterogeneous data?
  6. 6. Multimedia Retrieval Problem • Given a query (either image or video), retrieve relevant items from a (large) set of multimedia files
  7. 7. Image/Video Representation • Each keypoint descriptor is in high dimensional space • Each image/keyframe is represented as a sparse set of points, each point in high dimensional space • Search: matching between two images will take considerable time!!
  8. 8. Powerpoint Presentation Indexing and Search • Indexing • Stemmed text is indexed with their name, value pairs(slidenumber, slidetitle, slidetext) • The set of slides belonging to a presentation file are mapped relationally to that presentation along with the values of presentation title and presentation filename • The keywords will be stored as an inverted index (Given a keyword, the set of slides(and presentations) in which the keyword is found is mapped as an inverted listing) • Search • The presentations(slides in actual) are searched for matches in keywords • A presentation’s relevancy is calculated by the following : • The score of each slide that belong to the same presentation is summed up • The presentations are ranked according to their total score of relevancy (higher to lower)
  9. 9. Lecture Video • In order to find where the slide exists in a video, we need to segment the lecture video • We determine the transition of videos that are currently recorded using a software • For the videos recorded prior, we can use image processing techniques to get the transition • Once transition is found we can easily determine the duration of the slide segment of video
  10. 10. Textbook • We use the textbook back index and the ontology to form our index • The book’s index words and page numbers of the word’s occurrences are organized as the following XML <Textbook title = ‘textbookTitle’ > <Keyword> <Word> index word </Word> <PageNumber>1,2,3 </PageNumber> <Keyword> </Textbook> • The above information is indexed using Apache Lucene
  11. 11. Our Objectives for UCS • Create a program that will accurately search all electronic course materials • Integrate UCS into Courses • Help students understand learning preferences as connected to UCS • Create a user friendly, clean interface • Determine the effectiveness of the tool
  12. 12. The Research • Developed the Ultimate Course Search Tool – Beta • Begun Collecting Data in a Security Course • Control and Experimental • Demographics, Pre-Post Test, ILS
  13. 13. Learning Preferences • Index of Learning Preferences (Felder & Soloman, 1993) Four Types of Learners • Active – Reflective • Sensing – Intuitive • Visual – Verbal • Sequential - Global
  14. 14. Your Results • ACT_______________________________________REF 11a 9a 7a 5a 3a 1a 1b 3b 5b 7b 9b 11b • SEN________________________________________INT 11a 9a 7a 5a 3a 1a 1b 3b 5b 7b 9b 11b • VIS________________________________________VRB 11a 9a 7a 5a 3a 1a 1b 3b 5b 7b 9b 11b • SEQ________________________________________GLO 11a 9a 7a 5a 3a 1a 1b 3b 5b 7b 9b 11b
  15. 15. Student Learning Preferences Control • 2 Active • 12 Reflective • 11 Sensing • 3 Intuitive • 13 Visual • 1 Verbal • 7 Sequential • 7 Global Experimental • 10 Active • 9 Reflective • 15 Sensing • 4 Intuitive • 17 Visual • 2 Verbal • 12 Sequential • 7 Global
  16. 16. Student Demographics Control • N = 28 • Mean Age = 23.8 • Year in School = 3.54 • Gender • Female = 4 • Male = 24 • Racial/Ethnic Identifiers • African American/Black = 5 • American Indian or Alaska = 0 • Asian = 3 • Caucasian/White = 12 • Hispanic/Latino = 9 • Pacific Isl/Native Hawiian = 1 • Other = 4 • No Answer = 3 Experimental • N = 21 • Mean Age = 23.19 • Year in School = 3.52 • Gender • Female = 1 • Male = 20 • Racial/Ethnic Identifiers • African American/Black = 2 • American Indian or Alaska = 1 • Asian = 6 • Caucasian/White = 6 • Hispanic/Latino = 8 • Pacific Isl/Native Hawiian = 1 • Other = 5 • No Answer = 0
  17. 17. Survey Feedback: How did the students using UCS? • Search for Information/specific words & terms • Review video podcast lectures • As a reference • To study for the Midterm and Final • To help complete class projects
  18. 18. Survey Feedback: What did the students like about UCS? • User friendly • Search engine • Fast and accurate • Search exact words • Tabs and specific information • Search Videos • Searches lead to a lot of information • Helped Students Understand Concepts • Made studying easier • Able to better understand material covered in class
  19. 19. Pre and Post Test Results Control • Pre Test Mean = 9.39 • Standard Dev = 2.25 • Post Test Mean = 12.13 • Standard Dev = 2.29 • Change in Scores = 2.74 Experimental • Pre Test Mean = 9.10 • Standard Dev = 2.16 • Post Test Mean = 11.70 • Standard Dev = 3.09 • Change in Scores = 2.60
  20. 20. Implications for Higher Education • Reduce attrition • Increase clarity of course organization • Increase student interaction with materials • Individualize learning • Create connections within and between courses
  21. 21. In the Future…. • In the Fall – integrate into Hybrid Graduate Counseling course and MSU Computer Science Course • UCS will have individual learning preferences assessment and information accessible in-tool • UCS will be integrated into a course management system – like Moodle or Canvas
  22. 22. In the Future…. • UCS will Learn from the Students – and Provide Search Terms in Preferential Order Based on Learning Preferences and Previous Viewings of Material • UCS will be linked to a database of courses • More buttons! UCS will have the ability to add more types of materials – with more buttons
  23. 23. Questions? • Our Youtube Channel: http://bit.ly/1imcF8o • This Presentation on Slideshare:
  24. 24. The Tool!

×