Predicting Video Lecture Complexity

  • 1. Mansi Gera 2. Prachi Servanshi 3. Simran Kaur
  • In the past decade, use of Massively Open Online Courses (MOOCs) has rapidly risen, providing access to higher education to millions of students . MOOCs have also changed the education paradigm, with most courses involving a combination of short video lectures with moderated online discussion. This project evaluates performance of different supervised regression algorithms and features to predict lecture video complexity. The results of this work will help the MOOC instructors tailor their teaching style to virtual audiences for improving the level and ease of understanding.

  • Students, teachers or anyone who study from online courses. Students can access the video lectures for acquiring information. Whereas the instructors can easily analyse the complex regions in the videos that allows them to alter the content in an appropriate way that enables easier understanding of students.

  • https://docs.google.com/spreadsheets/d/1VOATolHWtkYIc58hY-J1jvHwvds9z2qdP-X8KQyV8ME/edit?usp=sharing

  • Before -  As of now, people who study/learn online, face difficulties in some portions of the video which is difficult to interpret and they have pause and play again and again to understand it. So there should be a mechanism through which instructor can get to know about it and he can work on it.

    After - This project will help the instructor by predicting the areas where the possibility of that portions of video which is difficult to understand is high so that he can work on it more to deliver easy to learn video lecture. This will be helpful to both instructor and the students who learn online.

October 20, 2019

0 responses on "Predicting Video Lecture Complexity"

Leave a Message

Your email address will not be published.


Knowledge and Content by Li2 Technologies | © 2021 NASSCOM Foundation | All rights reserved