Online Social Community Sub-Location Classification

Jiarui Wang; Xiaoyun Wang; Chun Ming Lai; S. Felix Wu

doi:10.1145/3625007.3627504

Online Social Community Sub-Location Classification

Jiarui Wang, Xiaoyun Wang, Chun Ming Lai, S. Felix Wu

Department of Electrical Engineering

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

Abstract

Facebook public pages are a popular form of online social network (OSN) communities. The "like"connections between public pages create a graph of pages on Facebook. Geographic location is a crucial piece of metadata for pages, but it is often omitted by page managers. We propose a classification algorithm to restore the missing subdivision location of Facebook public pages. We propose neighborhood state distribution vectors as features for graph neural networks to classify the state of the pages. Then, we define intrastate and interstate Facebook public pages based on the high-probability state label outputted by the classification model. Finally, we profile states with different influences over the online communities by analyzing the classification confusion matrix, interstate page percentages, and interstate pages across state borders. Our method achieves better accuracy (87.52%) and F1 score (0.8756) than previous studies (66.2% and 73.08%).

Original language	English
Title of host publication	Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023
Editors	B. Aditya Prakash, Dong Wang, Tim Weninger
Publisher	Association for Computing Machinery, Inc
Pages	276-280
Number of pages	5
ISBN (Electronic)	9798400704093
DOIs	https://doi.org/10.1145/3625007.3627504
Publication status	Published - 2023 Nov 6
Event	15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023 - Kusadasi, Turkey Duration: 2023 Nov 6 → 2023 Nov 9

Publication series

Name	Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023

Conference

Conference	15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023
Country/Territory	Turkey
City	Kusadasi
Period	23-11-06 → 23-11-09

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Information Systems
Information Systems and Management
Safety, Risk, Reliability and Quality
Social Psychology
Communication

Access to Document

10.1145/3625007.3627504

Cite this

Wang, J., Wang, X., Lai, C. M., & Wu, S. F. (2023). Online Social Community Sub-Location Classification. In B. Aditya Prakash, D. Wang, & T. Weninger (Eds.), Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023 (pp. 276-280). (Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023). Association for Computing Machinery, Inc. https://doi.org/10.1145/3625007.3627504

Wang, Jiarui ; Wang, Xiaoyun ; Lai, Chun Ming et al. / Online Social Community Sub-Location Classification. Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023. editor / B. Aditya Prakash ; Dong Wang ; Tim Weninger. Association for Computing Machinery, Inc, 2023. pp. 276-280 (Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023).

@inproceedings{e0ac0f0f0da748cea32fff6cc0df1a9d,

title = "Online Social Community Sub-Location Classification",

abstract = "Facebook public pages are a popular form of online social network (OSN) communities. The {"}like{"}connections between public pages create a graph of pages on Facebook. Geographic location is a crucial piece of metadata for pages, but it is often omitted by page managers. We propose a classification algorithm to restore the missing subdivision location of Facebook public pages. We propose neighborhood state distribution vectors as features for graph neural networks to classify the state of the pages. Then, we define intrastate and interstate Facebook public pages based on the high-probability state label outputted by the classification model. Finally, we profile states with different influences over the online communities by analyzing the classification confusion matrix, interstate page percentages, and interstate pages across state borders. Our method achieves better accuracy (87.52%) and F1 score (0.8756) than previous studies (66.2% and 73.08%).",

author = "Jiarui Wang and Xiaoyun Wang and Lai, {Chun Ming} and Wu, {S. Felix}",

note = "Publisher Copyright: {\textcopyright} 2023 Owner/Author(s).; 15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023 ; Conference date: 06-11-2023 Through 09-11-2023",

year = "2023",

month = nov,

day = "6",

doi = "10.1145/3625007.3627504",

language = "English",

series = "Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023",

publisher = "Association for Computing Machinery, Inc",

pages = "276--280",

editor = "{Aditya Prakash}, B. and Dong Wang and Tim Weninger",

booktitle = "Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023",

}

Wang, J, Wang, X, Lai, CM & Wu, SF 2023, Online Social Community Sub-Location Classification. in B Aditya Prakash, D Wang & T Weninger (eds), Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023. Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023, Association for Computing Machinery, Inc, pp. 276-280, 15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023, Kusadasi, Turkey, 23-11-06. https://doi.org/10.1145/3625007.3627504

Online Social Community Sub-Location Classification. / Wang, Jiarui; Wang, Xiaoyun; Lai, Chun Ming et al.
Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023. ed. / B. Aditya Prakash; Dong Wang; Tim Weninger. Association for Computing Machinery, Inc, 2023. p. 276-280 (Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023).

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

TY - GEN

T1 - Online Social Community Sub-Location Classification

AU - Wang, Jiarui

AU - Wang, Xiaoyun

AU - Lai, Chun Ming

AU - Wu, S. Felix

PY - 2023/11/6

Y1 - 2023/11/6

N2 - Facebook public pages are a popular form of online social network (OSN) communities. The "like"connections between public pages create a graph of pages on Facebook. Geographic location is a crucial piece of metadata for pages, but it is often omitted by page managers. We propose a classification algorithm to restore the missing subdivision location of Facebook public pages. We propose neighborhood state distribution vectors as features for graph neural networks to classify the state of the pages. Then, we define intrastate and interstate Facebook public pages based on the high-probability state label outputted by the classification model. Finally, we profile states with different influences over the online communities by analyzing the classification confusion matrix, interstate page percentages, and interstate pages across state borders. Our method achieves better accuracy (87.52%) and F1 score (0.8756) than previous studies (66.2% and 73.08%).

AB - Facebook public pages are a popular form of online social network (OSN) communities. The "like"connections between public pages create a graph of pages on Facebook. Geographic location is a crucial piece of metadata for pages, but it is often omitted by page managers. We propose a classification algorithm to restore the missing subdivision location of Facebook public pages. We propose neighborhood state distribution vectors as features for graph neural networks to classify the state of the pages. Then, we define intrastate and interstate Facebook public pages based on the high-probability state label outputted by the classification model. Finally, we profile states with different influences over the online communities by analyzing the classification confusion matrix, interstate page percentages, and interstate pages across state borders. Our method achieves better accuracy (87.52%) and F1 score (0.8756) than previous studies (66.2% and 73.08%).

UR - http://www.scopus.com/inward/record.url?scp=85190627667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85190627667&partnerID=8YFLogxK

U2 - 10.1145/3625007.3627504

DO - 10.1145/3625007.3627504

M3 - Conference contribution

AN - SCOPUS:85190627667

T3 - Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023

SP - 276

EP - 280

BT - Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023

A2 - Aditya Prakash, B.

A2 - Wang, Dong

A2 - Weninger, Tim

PB - Association for Computing Machinery, Inc

T2 - 15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023

Y2 - 6 November 2023 through 9 November 2023

ER -

Wang J, Wang X, Lai CM, Wu SF. Online Social Community Sub-Location Classification. In Aditya Prakash B, Wang D, Weninger T, editors, Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023. Association for Computing Machinery, Inc. 2023. p. 276-280. (Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023). doi: 10.1145/3625007.3627504

Online Social Community Sub-Location Classification

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this