Abstract

Lecture videos are a widely used resource for learning. A simple way to create videos is to record live lectures, but these videos end up being lengthy, include long pauses and repetitive words making the viewing experience time consuming. While pauses are useful in live learning environments where students take notes, we question the value of pauses in video lectures. Techniques and algorithms that can shorten such videos can have a huge impact in saving students' time and reducing storage space. We study this problem of shortening videos by removing long pauses and adaptively modifying the playback rate by emphasizing the most important sections ofthe video and its effect on the student community. The playback rate is designed in such a way to play uneventful sections faster and significant sections slower. Important and unimportant sections of a video are identified using textual analysis. We use an existing speech-to-text algorithm to extract the transcript and apply latent semantic analysis and standard information retrieval techniques to identify the relevant segments of the video. We compute relevance scores of different segments and propose a variable playback rate for each of these segments. The aim is to reduce the amount of time students spend on passive learning while watching videos without harming their ability to follow the lecture. We validate our approach by conducting a user study among computer science students and measuring their engagement. The results indicate no significant difference in their engagement when our method is compared to the original unedited video.

Original languageEnglish (US)
Title of host publicationProceedings of the 12th International Conference on e-Learning, ICEL 2017
PublisherAcademic Conferences Limited
Pages267-276
Number of pages10
ISBN (Electronic)9781911218357
StatePublished - 2017
Event12th International Conference on e-Learning, ICEL 2017 - Orlando, United States
Duration: Jun 1 2017Jun 2 2017

Other

Other12th International Conference on e-Learning, ICEL 2017
CountryUnited States
CityOrlando
Period6/1/176/2/17

Fingerprint

video
Students
Information retrieval
Computer science
student
Semantics
time
time experience
information retrieval
computer science
learning
learning environment
semantics
ability
resources
community
Values

Keywords

  • Playback rate
  • Temporal compression
  • Video lectures

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science Applications
  • Information Systems
  • Education

Cite this

Shenoy, S. P., Amresh, A., & Femiani, J. (2017). An adaptive time reduction technique for video lectures. In Proceedings of the 12th International Conference on e-Learning, ICEL 2017 (pp. 267-276). Academic Conferences Limited.

An adaptive time reduction technique for video lectures. / Shenoy, Sreenivas Purushothama; Amresh, Ashish; Femiani, John.

Proceedings of the 12th International Conference on e-Learning, ICEL 2017. Academic Conferences Limited, 2017. p. 267-276.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shenoy, SP, Amresh, A & Femiani, J 2017, An adaptive time reduction technique for video lectures. in Proceedings of the 12th International Conference on e-Learning, ICEL 2017. Academic Conferences Limited, pp. 267-276, 12th International Conference on e-Learning, ICEL 2017, Orlando, United States, 6/1/17.
Shenoy SP, Amresh A, Femiani J. An adaptive time reduction technique for video lectures. In Proceedings of the 12th International Conference on e-Learning, ICEL 2017. Academic Conferences Limited. 2017. p. 267-276
Shenoy, Sreenivas Purushothama ; Amresh, Ashish ; Femiani, John. / An adaptive time reduction technique for video lectures. Proceedings of the 12th International Conference on e-Learning, ICEL 2017. Academic Conferences Limited, 2017. pp. 267-276
@inproceedings{2b93da6a0803482ba77553670c70fdf3,
title = "An adaptive time reduction technique for video lectures",
abstract = "Lecture videos are a widely used resource for learning. A simple way to create videos is to record live lectures, but these videos end up being lengthy, include long pauses and repetitive words making the viewing experience time consuming. While pauses are useful in live learning environments where students take notes, we question the value of pauses in video lectures. Techniques and algorithms that can shorten such videos can have a huge impact in saving students' time and reducing storage space. We study this problem of shortening videos by removing long pauses and adaptively modifying the playback rate by emphasizing the most important sections ofthe video and its effect on the student community. The playback rate is designed in such a way to play uneventful sections faster and significant sections slower. Important and unimportant sections of a video are identified using textual analysis. We use an existing speech-to-text algorithm to extract the transcript and apply latent semantic analysis and standard information retrieval techniques to identify the relevant segments of the video. We compute relevance scores of different segments and propose a variable playback rate for each of these segments. The aim is to reduce the amount of time students spend on passive learning while watching videos without harming their ability to follow the lecture. We validate our approach by conducting a user study among computer science students and measuring their engagement. The results indicate no significant difference in their engagement when our method is compared to the original unedited video.",
keywords = "Playback rate, Temporal compression, Video lectures",
author = "Shenoy, {Sreenivas Purushothama} and Ashish Amresh and John Femiani",
year = "2017",
language = "English (US)",
pages = "267--276",
booktitle = "Proceedings of the 12th International Conference on e-Learning, ICEL 2017",
publisher = "Academic Conferences Limited",

}

TY - GEN

T1 - An adaptive time reduction technique for video lectures

AU - Shenoy, Sreenivas Purushothama

AU - Amresh, Ashish

AU - Femiani, John

PY - 2017

Y1 - 2017

N2 - Lecture videos are a widely used resource for learning. A simple way to create videos is to record live lectures, but these videos end up being lengthy, include long pauses and repetitive words making the viewing experience time consuming. While pauses are useful in live learning environments where students take notes, we question the value of pauses in video lectures. Techniques and algorithms that can shorten such videos can have a huge impact in saving students' time and reducing storage space. We study this problem of shortening videos by removing long pauses and adaptively modifying the playback rate by emphasizing the most important sections ofthe video and its effect on the student community. The playback rate is designed in such a way to play uneventful sections faster and significant sections slower. Important and unimportant sections of a video are identified using textual analysis. We use an existing speech-to-text algorithm to extract the transcript and apply latent semantic analysis and standard information retrieval techniques to identify the relevant segments of the video. We compute relevance scores of different segments and propose a variable playback rate for each of these segments. The aim is to reduce the amount of time students spend on passive learning while watching videos without harming their ability to follow the lecture. We validate our approach by conducting a user study among computer science students and measuring their engagement. The results indicate no significant difference in their engagement when our method is compared to the original unedited video.

AB - Lecture videos are a widely used resource for learning. A simple way to create videos is to record live lectures, but these videos end up being lengthy, include long pauses and repetitive words making the viewing experience time consuming. While pauses are useful in live learning environments where students take notes, we question the value of pauses in video lectures. Techniques and algorithms that can shorten such videos can have a huge impact in saving students' time and reducing storage space. We study this problem of shortening videos by removing long pauses and adaptively modifying the playback rate by emphasizing the most important sections ofthe video and its effect on the student community. The playback rate is designed in such a way to play uneventful sections faster and significant sections slower. Important and unimportant sections of a video are identified using textual analysis. We use an existing speech-to-text algorithm to extract the transcript and apply latent semantic analysis and standard information retrieval techniques to identify the relevant segments of the video. We compute relevance scores of different segments and propose a variable playback rate for each of these segments. The aim is to reduce the amount of time students spend on passive learning while watching videos without harming their ability to follow the lecture. We validate our approach by conducting a user study among computer science students and measuring their engagement. The results indicate no significant difference in their engagement when our method is compared to the original unedited video.

KW - Playback rate

KW - Temporal compression

KW - Video lectures

UR - http://www.scopus.com/inward/record.url?scp=85027854733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027854733&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85027854733

SP - 267

EP - 276

BT - Proceedings of the 12th International Conference on e-Learning, ICEL 2017

PB - Academic Conferences Limited

ER -