Asee peer logo

Student Preference of Video Length for Studying Machine Learning in a Flipped Classroom

Download Paper |

Conference

2023 ASEE Annual Conference & Exposition

Location

Baltimore , Maryland

Publication Date

June 25, 2023

Start Date

June 25, 2023

End Date

June 28, 2023

Conference Session

COED: Student Perspectives of Instructional and Advising Approaches

Tagged Division

Computers in Education Division (COED)

Page Count

11

DOI

10.18260/1-2--44322

Permanent URL

https://peer.asee.org/44322

Download Count

261

Paper Authors

biography

Ahmed Dallal University of Pittsburgh Orcid 16x16 orcid.org/0000-0003-0573-2326

visit author page

Dr. Dallal is an assistant professor at the department of electrical and computer engineering, University of Pittsburgh, since August 2017. Dr. Dallal's primary focus is on education development and innovation. His research interests include biomedical signal processing, biomedical image analysis, computer vision, machine learning, networked control systems, and human-machine learning.

visit author page

Download Paper |

Abstract

In recent years, the flipped classroom has emerged as an increasingly popular teaching method in higher education, as it is seen as an effective way to promote active learning among students. Nevertheless, a crucial factor that has not been studied in-depth is students' preference for the length of videos in the flipped classroom. Although a few studies have considered the design process of videos and students' preferences for video length in a flipped classroom, there are varying recommendations, and a lack of data-driven analysis on how many and how long the videos should be. In this study, we investigated students' preference for video length in flipped machine learning classes offered during the spring and fall semesters of 2022. The flipped modules of this course include video lectures that vary in length, ranging from 4 to 20 minutes. Depending on the video's length, we required students to finish between three to seven video lessons before class time. To analyze student interaction with videos of different lengths, we statistically analyzed the video coverage from different modules and used surveys to gather students' preferences for video length. Our analysis indicated that the number of students completing videos before class time significantly decreased as video duration increased. However, once students started a video, they completed most of it irrespective of its length. Statistical analysis of homework scores did not show any significant difference in students' performance in modules with short videos compared to those with long videos. In response to the survey, a considerable percentage of students indicated their preference for short videos, as it helped them maintain focus. However, a higher percentage of students acknowledged that despite the varied video durations, the lengths were suitable for the presented topics. This suggests that relatively longer videos could be acceptable if the nature of the topic requires it. However, these videos should be interactive to help maintain students' attention.

Dallal, A. (2023, June), Student Preference of Video Length for Studying Machine Learning in a Flipped Classroom Paper presented at 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland. 10.18260/1-2--44322

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2023 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015