How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies

Min Gyeong Choe; Jae Hong Park; Dong Won Seo

doi:10.1007/978-3-030-22784-5_19

How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies

Min Gyeong Choe, Jae Hong Park, Dong Won Seo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

YouTube has become one of the most influential channels in recent years. There are an enormous number of videos on the platform, but few of them are popular, getting placed in the “Trending” section. But, videos on this list have different stories. Some of them will get constant popularity and others will fade out. Many researchers have analyzed what will make a video become popular. However, no study has focused on how long a video maintains its popularity. In addition, the content similarity between the thumbnail image and the title has been neglected, although it appears to play an important role in social media posts (e.g. blogs, Instagram). We measure the variable, content similarity, by analyzing the thumbnail image and text. This study investigates the impact of this new variable on popular videos’ survival to give YouTubers and advertisers insights into video marketing. Also, our suggested approach can achieve new academic results in the research of YouTube.

Original language	English
Title of host publication	The Ecosystem of e-Business
Subtitle of host publication	Technologies, Stakeholders, and Connections - 17th Workshop on e-Business, WeB 2018, Revised Selected Papers
Editors	Jennifer J. Xu, Bin Zhu, Xiao Liu, Michael J. Shaw, Han Zhang, Ming Fan
Publisher	Springer Verlag
Pages	190-197
Number of pages	8
ISBN (Print)	9783030227838
DOIs	https://doi.org/10.1007/978-3-030-22784-5_19
Publication status	Published - 2019
Event	17th Annual Workshop on e-Business, WeB 2018 - Santa Clara, United States Duration: 12 Dec 2018 → 12 Dec 2018

Publication series

Name	Lecture Notes in Business Information Processing
Volume	357
ISSN (Print)	1865-1348
ISSN (Electronic)	1865-1356

Conference

Conference	17th Annual Workshop on e-Business, WeB 2018
Country/Territory	United States
City	Santa Clara
Period	12/12/18 → 12/12/18

Bibliographical note

Publisher Copyright:
© Springer Nature Switzerland AG 2019.

Keywords

Content similarity
Deep learning method
Video popularity
YouTube trending

Access to Document

10.1007/978-3-030-22784-5_19

Cite this

Choe, M. G., Park, J. H., & Seo, D. W. (2019). How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies. In J. J. Xu, B. Zhu, X. Liu, M. J. Shaw, H. Zhang, & M. Fan (Eds.), The Ecosystem of e-Business: Technologies, Stakeholders, and Connections - 17th Workshop on e-Business, WeB 2018, Revised Selected Papers (pp. 190-197). (Lecture Notes in Business Information Processing; Vol. 357). Springer Verlag. https://doi.org/10.1007/978-3-030-22784-5_19

Choe, Min Gyeong ; Park, Jae Hong ; Seo, Dong Won. / How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies. The Ecosystem of e-Business: Technologies, Stakeholders, and Connections - 17th Workshop on e-Business, WeB 2018, Revised Selected Papers. editor / Jennifer J. Xu ; Bin Zhu ; Xiao Liu ; Michael J. Shaw ; Han Zhang ; Ming Fan. Springer Verlag, 2019. pp. 190-197 (Lecture Notes in Business Information Processing).

@inproceedings{0eed5014a9d847b88c4b5193bcf291b9,

title = "How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies",

abstract = "YouTube has become one of the most influential channels in recent years. There are an enormous number of videos on the platform, but few of them are popular, getting placed in the “Trending” section. But, videos on this list have different stories. Some of them will get constant popularity and others will fade out. Many researchers have analyzed what will make a video become popular. However, no study has focused on how long a video maintains its popularity. In addition, the content similarity between the thumbnail image and the title has been neglected, although it appears to play an important role in social media posts (e.g. blogs, Instagram). We measure the variable, content similarity, by analyzing the thumbnail image and text. This study investigates the impact of this new variable on popular videos{\textquoteright} survival to give YouTubers and advertisers insights into video marketing. Also, our suggested approach can achieve new academic results in the research of YouTube.",

keywords = "Content similarity, Deep learning method, Video popularity, YouTube trending",

author = "Choe, {Min Gyeong} and Park, {Jae Hong} and Seo, {Dong Won}",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 17th Annual Workshop on e-Business, WeB 2018 ; Conference date: 12-12-2018 Through 12-12-2018",

year = "2019",

doi = "10.1007/978-3-030-22784-5_19",

language = "English",

isbn = "9783030227838",

series = "Lecture Notes in Business Information Processing",

publisher = "Springer Verlag",

pages = "190--197",

editor = "Xu, {Jennifer J.} and Bin Zhu and Xiao Liu and Shaw, {Michael J.} and Han Zhang and Ming Fan",

booktitle = "The Ecosystem of e-Business",

address = "Germany",

}

Choe, MG, Park, JH & Seo, DW 2019, How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies. in JJ Xu, B Zhu, X Liu, MJ Shaw, H Zhang & M Fan (eds), The Ecosystem of e-Business: Technologies, Stakeholders, and Connections - 17th Workshop on e-Business, WeB 2018, Revised Selected Papers. Lecture Notes in Business Information Processing, vol. 357, Springer Verlag, pp. 190-197, 17th Annual Workshop on e-Business, WeB 2018, Santa Clara, United States, 12/12/18. https://doi.org/10.1007/978-3-030-22784-5_19

How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies. / Choe, Min Gyeong; Park, Jae Hong ; Seo, Dong Won.
The Ecosystem of e-Business: Technologies, Stakeholders, and Connections - 17th Workshop on e-Business, WeB 2018, Revised Selected Papers. ed. / Jennifer J. Xu; Bin Zhu; Xiao Liu; Michael J. Shaw; Han Zhang; Ming Fan. Springer Verlag, 2019. p. 190-197 (Lecture Notes in Business Information Processing; Vol. 357).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies

AU - Choe, Min Gyeong

AU - Park, Jae Hong

AU - Seo, Dong Won

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2019.

PY - 2019

Y1 - 2019

N2 - YouTube has become one of the most influential channels in recent years. There are an enormous number of videos on the platform, but few of them are popular, getting placed in the “Trending” section. But, videos on this list have different stories. Some of them will get constant popularity and others will fade out. Many researchers have analyzed what will make a video become popular. However, no study has focused on how long a video maintains its popularity. In addition, the content similarity between the thumbnail image and the title has been neglected, although it appears to play an important role in social media posts (e.g. blogs, Instagram). We measure the variable, content similarity, by analyzing the thumbnail image and text. This study investigates the impact of this new variable on popular videos’ survival to give YouTubers and advertisers insights into video marketing. Also, our suggested approach can achieve new academic results in the research of YouTube.

AB - YouTube has become one of the most influential channels in recent years. There are an enormous number of videos on the platform, but few of them are popular, getting placed in the “Trending” section. But, videos on this list have different stories. Some of them will get constant popularity and others will fade out. Many researchers have analyzed what will make a video become popular. However, no study has focused on how long a video maintains its popularity. In addition, the content similarity between the thumbnail image and the title has been neglected, although it appears to play an important role in social media posts (e.g. blogs, Instagram). We measure the variable, content similarity, by analyzing the thumbnail image and text. This study investigates the impact of this new variable on popular videos’ survival to give YouTubers and advertisers insights into video marketing. Also, our suggested approach can achieve new academic results in the research of YouTube.

KW - Content similarity

KW - Deep learning method

KW - Video popularity

KW - YouTube trending

UR - http://www.scopus.com/inward/record.url?scp=85069203024&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-22784-5_19

DO - 10.1007/978-3-030-22784-5_19

M3 - Conference contribution

AN - SCOPUS:85069203024

SN - 9783030227838

T3 - Lecture Notes in Business Information Processing

SP - 190

EP - 197

BT - The Ecosystem of e-Business

A2 - Xu, Jennifer J.

A2 - Zhu, Bin

A2 - Liu, Xiao

A2 - Shaw, Michael J.

A2 - Zhang, Han

A2 - Fan, Ming

PB - Springer Verlag

T2 - 17th Annual Workshop on e-Business, WeB 2018

Y2 - 12 December 2018 through 12 December 2018

ER -

Choe MG, Park JH , Seo DW. How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies. In Xu JJ, Zhu B, Liu X, Shaw MJ, Zhang H, Fan M, editors, The Ecosystem of e-Business: Technologies, Stakeholders, and Connections - 17th Workshop on e-Business, WeB 2018, Revised Selected Papers. Springer Verlag. 2019. p. 190-197. (Lecture Notes in Business Information Processing). doi: 10.1007/978-3-030-22784-5_19

How Long Will Your Videos Remain Popular? Empirical Study of the Impact of Video Features on YouTube Trending Using Deep Learning Methodologies

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this