CLEFT: Contextualised unified Learning of User Engagement in Video Lectures with Feedback
CLEFT: Contextualised unified Learning of User Engagement in Video Lectures with Feedback
Predicting contextualised engagement in videos is a long-standing problem that has been popularly attempted by exploiting the number of views or likes using different computational methods. The recent decade has seen a boom in online learning resources, and during the pandemic, there has been an exponential rise of online teaching videos without much quality control. As a result, we are faced with two key challenges. First, how to decide which lecture videos are engaging to intrigue the listener and increase productivity, and second, how to automatically provide feedback to the content creator using which they could improve the content. The quality of the content could be improved if the creators could automatically get constructive feedback on their content. On the other hand, there has been a steep rise in developing computational methods to predict a user engagement score. In this paper, we have proposed a new unified model, CLEFT, that means “Contextualised unified Learning of user Engagement in video lectures with Feedback” that learns from the features extracted from freely available public online teaching videos and provides feedback on the video along with the user engagement score. Given the complexity of the task, our unified framework employs different pre-trained models working together as an ensemble of classifiers. Our model exploits a range of multi-modal features to model the complexity of language, context agnostic information, textual emotion of the delivered content, animation, speaker’s pitch, and speech emotions. Our results support hypothesis that proposed model can detect engagement reliably and the feedback component gives useful insights to the content creator to further help improve the content.
BERT, NLP, contextual language models, emotions, text-based emotions, video engagement
17707-17720
Roy, Sujit
cfc4159e-80f0-4c04-a4aa-ff012c350788
Gaur, Vishal
1d2cda70-6210-400d-a862-b78bbf4604f1
Razah, Haider
7d96403c-d857-4c37-af9d-de12b63035e5
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
23 February 2023
Roy, Sujit
cfc4159e-80f0-4c04-a4aa-ff012c350788
Gaur, Vishal
1d2cda70-6210-400d-a862-b78bbf4604f1
Razah, Haider
7d96403c-d857-4c37-af9d-de12b63035e5
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
Roy, Sujit, Gaur, Vishal, Razah, Haider and Jameel, Shoaib
(2023)
CLEFT: Contextualised unified Learning of User Engagement in Video Lectures with Feedback.
IEEE Access, 11, .
(doi:10.1109/ACCESS.2023.3245982).
Abstract
Predicting contextualised engagement in videos is a long-standing problem that has been popularly attempted by exploiting the number of views or likes using different computational methods. The recent decade has seen a boom in online learning resources, and during the pandemic, there has been an exponential rise of online teaching videos without much quality control. As a result, we are faced with two key challenges. First, how to decide which lecture videos are engaging to intrigue the listener and increase productivity, and second, how to automatically provide feedback to the content creator using which they could improve the content. The quality of the content could be improved if the creators could automatically get constructive feedback on their content. On the other hand, there has been a steep rise in developing computational methods to predict a user engagement score. In this paper, we have proposed a new unified model, CLEFT, that means “Contextualised unified Learning of user Engagement in video lectures with Feedback” that learns from the features extracted from freely available public online teaching videos and provides feedback on the video along with the user engagement score. Given the complexity of the task, our unified framework employs different pre-trained models working together as an ensemble of classifiers. Our model exploits a range of multi-modal features to model the complexity of language, context agnostic information, textual emotion of the delivered content, animation, speaker’s pitch, and speech emotions. Our results support hypothesis that proposed model can detect engagement reliably and the feedback component gives useful insights to the content creator to further help improve the content.
This record has no associated files available for download.
More information
Accepted/In Press date: 8 February 2023
e-pub ahead of print date: 15 February 2023
Published date: 23 February 2023
Additional Information:
Funding Information:
This work was supported by Brainalive Research Pvt. Ltd., Kanpur, India (http://braina.live/). The work of Haider Raza was supported by the Economic and Social Research Council (ESRC) funded by the Business and Local Government Data Research Centre under Grant ES/S007156/1.
Publisher Copyright:
© 2013 IEEE.
Keywords:
BERT, NLP, contextual language models, emotions, text-based emotions, video engagement
Identifiers
Local EPrints ID: 476772
URI: http://eprints.soton.ac.uk/id/eprint/476772
ISSN: 2169-3536
PURE UUID: bf0c1cf0-d6eb-4ba5-982a-d5a9133fd909
Catalogue record
Date deposited: 15 May 2023 16:59
Last modified: 17 Mar 2024 02:12
Export record
Altmetrics
Contributors
Author:
Sujit Roy
Author:
Vishal Gaur
Author:
Haider Razah
Author:
Shoaib Jameel
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics