Influence in Social Networks Through Visual Analysis of Image Memes

Carles Onielfa; Carles Casacuberta; Sergio Escalera

doi:10.3233/FAIA220317

Influence in Social Networks Through Visual Analysis of Image Memes

Carles Onielfa^*, Carles Casacuberta, Sergio Escalera

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

54 Downloads (Pure)

Abstract

Memes evolve and mutate through their diffusion in social media. They have the potential to propagate ideas and, by extension, products. Many studies have focused on memes, but none so far, to our knowledge, on the users that post them, their relationships, and the reach of their influence. In this article, we define a meme influence graph together with suitable metrics to visualize and quantify influence between users who post memes, and we also describe a process to implement our definitions using a new approach to meme detection based on text-to-image area ratio and contrast. After applying our method to a set of users of the social media platform Instagram, we conclude that our metrics add information to already existing user characteristics.

Original language	English
Title of host publication	Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence
Editors	Atia Cortes, Francisco Grimaldo, Tommaso Flaminio
Number of pages	10
Publisher	IOS Press
Publication date	17 Oct 2022
Pages	71-80
ISBN (Electronic)	9781643683263
DOIs	https://doi.org/10.3233/FAIA220317
Publication status	Published - 17 Oct 2022
Externally published	Yes
Event	24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022 - Sitges, Spain Duration: 19 Oct 2022 → 21 Oct 2022

Conference

Conference	24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022
Country/Territory	Spain
City	Sitges
Period	19/10/2022 → 21/10/2022

Series	Frontiers in Artificial Intelligence and Applications
Volume	356
ISSN	0922-6389

Bibliographical note

Funding Information:
1Corresponding Author: Carles Onielfa, Universitat de Barcelona, Gran Via de les Corts Catalanes 585, 08007 Barcelona, Spain; carlesonielfa@gmail.com. This work has been partially supported by MICIN/AEI under projects PID2019-105093GB-I00 and PID2020-117971GB-C22, and by ICREA under the ICREA Academia programme.

Publisher Copyright:
© 2022 The authors and IOS Press.

Keywords

clustering
CNN
culture
DBSCAN
graph
influence
Memes
social media
social network

Access to Document

10.3233/FAIA220317Licence: CC BY-NC 4.0

Open Access articleFinal published version, 2.64 MBLicence: CC BY-NC 4.0

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Onielfa, C., Casacuberta, C., & Escalera, S. (2022). Influence in Social Networks Through Visual Analysis of Image Memes. In A. Cortes, F. Grimaldo, & T. Flaminio (Eds.), Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence (pp. 71-80). IOS Press. https://doi.org/10.3233/FAIA220317

Onielfa, Carles ; Casacuberta, Carles ; Escalera, Sergio. / Influence in Social Networks Through Visual Analysis of Image Memes. Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence. editor / Atia Cortes ; Francisco Grimaldo ; Tommaso Flaminio. IOS Press, 2022. pp. 71-80 (Frontiers in Artificial Intelligence and Applications, Vol. 356).

@inproceedings{663b3358ec2d41dfb378d73bb6f2f1e5,

title = "Influence in Social Networks Through Visual Analysis of Image Memes",

abstract = "Memes evolve and mutate through their diffusion in social media. They have the potential to propagate ideas and, by extension, products. Many studies have focused on memes, but none so far, to our knowledge, on the users that post them, their relationships, and the reach of their influence. In this article, we define a meme influence graph together with suitable metrics to visualize and quantify influence between users who post memes, and we also describe a process to implement our definitions using a new approach to meme detection based on text-to-image area ratio and contrast. After applying our method to a set of users of the social media platform Instagram, we conclude that our metrics add information to already existing user characteristics.",

keywords = "clustering, CNN, culture, DBSCAN, graph, influence, Memes, social media, social network",

author = "Carles Onielfa and Carles Casacuberta and Sergio Escalera",

note = "Funding Information: 1Corresponding Author: Carles Onielfa, Universitat de Barcelona, Gran Via de les Corts Catalanes 585, 08007 Barcelona, Spain; carlesonielfa@gmail.com. This work has been partially supported by MICIN/AEI under projects PID2019-105093GB-I00 and PID2020-117971GB-C22, and by ICREA under the ICREA Academia programme. Publisher Copyright: {\textcopyright} 2022 The authors and IOS Press.; 24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022 ; Conference date: 19-10-2022 Through 21-10-2022",

year = "2022",

month = oct,

day = "17",

doi = "10.3233/FAIA220317",

language = "English",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press",

pages = "71--80",

editor = "Atia Cortes and Francisco Grimaldo and Tommaso Flaminio",

booktitle = "Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence",

address = "Netherlands",

}

Onielfa, C, Casacuberta, C & Escalera, S 2022, Influence in Social Networks Through Visual Analysis of Image Memes. in A Cortes, F Grimaldo & T Flaminio (eds), Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence. IOS Press, Frontiers in Artificial Intelligence and Applications, vol. 356, pp. 71-80, 24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022, Sitges, Spain, 19/10/2022. https://doi.org/10.3233/FAIA220317

Influence in Social Networks Through Visual Analysis of Image Memes. / Onielfa, Carles; Casacuberta, Carles; Escalera, Sergio.
Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence. ed. / Atia Cortes; Francisco Grimaldo; Tommaso Flaminio. IOS Press, 2022. p. 71-80 (Frontiers in Artificial Intelligence and Applications, Vol. 356).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Influence in Social Networks Through Visual Analysis of Image Memes

AU - Onielfa, Carles

AU - Casacuberta, Carles

AU - Escalera, Sergio

N1 - Funding Information: 1Corresponding Author: Carles Onielfa, Universitat de Barcelona, Gran Via de les Corts Catalanes 585, 08007 Barcelona, Spain; carlesonielfa@gmail.com. This work has been partially supported by MICIN/AEI under projects PID2019-105093GB-I00 and PID2020-117971GB-C22, and by ICREA under the ICREA Academia programme. Publisher Copyright: © 2022 The authors and IOS Press.

PY - 2022/10/17

Y1 - 2022/10/17

N2 - Memes evolve and mutate through their diffusion in social media. They have the potential to propagate ideas and, by extension, products. Many studies have focused on memes, but none so far, to our knowledge, on the users that post them, their relationships, and the reach of their influence. In this article, we define a meme influence graph together with suitable metrics to visualize and quantify influence between users who post memes, and we also describe a process to implement our definitions using a new approach to meme detection based on text-to-image area ratio and contrast. After applying our method to a set of users of the social media platform Instagram, we conclude that our metrics add information to already existing user characteristics.

AB - Memes evolve and mutate through their diffusion in social media. They have the potential to propagate ideas and, by extension, products. Many studies have focused on memes, but none so far, to our knowledge, on the users that post them, their relationships, and the reach of their influence. In this article, we define a meme influence graph together with suitable metrics to visualize and quantify influence between users who post memes, and we also describe a process to implement our definitions using a new approach to meme detection based on text-to-image area ratio and contrast. After applying our method to a set of users of the social media platform Instagram, we conclude that our metrics add information to already existing user characteristics.

KW - clustering

KW - CNN

KW - culture

KW - DBSCAN

KW - graph

KW - influence

KW - Memes

KW - social media

KW - social network

UR - http://www.scopus.com/inward/record.url?scp=85141701755&partnerID=8YFLogxK

U2 - 10.3233/FAIA220317

DO - 10.3233/FAIA220317

M3 - Article in proceeding

AN - SCOPUS:85141701755

T3 - Frontiers in Artificial Intelligence and Applications

SP - 71

EP - 80

BT - Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence

A2 - Cortes, Atia

A2 - Grimaldo, Francisco

A2 - Flaminio, Tommaso

PB - IOS Press

T2 - 24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022

Y2 - 19 October 2022 through 21 October 2022

ER -

Onielfa C, Casacuberta C, Escalera S. Influence in Social Networks Through Visual Analysis of Image Memes. In Cortes A, Grimaldo F, Flaminio T, editors, Artificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence. IOS Press. 2022. p. 71-80. (Frontiers in Artificial Intelligence and Applications, Vol. 356). doi: 10.3233/FAIA220317

Influence in Social Networks Through Visual Analysis of Image Memes

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this