Social Network Influence Ranking via Embedding Network Interactions for User Recommendation

Hongbo Bo; Ryan McConville; Jun Hong; Weiru Liu

doi:10.1145/3366424.3383299

Social Network Influence Ranking via Embedding Network Interactions for User Recommendation

Hongbo Bo, Ryan McConville, Jun Hong, Weiru Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

16 Citations (Scopus)

397 Downloads (Pure)

Abstract

Within social networks user influence may be modelled based on user interactions. Further, it is typical to recommend users to others. What is the role of user influence in user recommendation? In this paper, we first propose to use a node embedding approach to integrate many types of interaction into embedded spaces where we then define a novel closeness measure to quantify the closeness of users based on interactions. We then propose a new influence ranking algorithm based on PageRank by incorporating the closeness
measure into the ranking mechanism. We evaluate our algorithm, EIRank, using a dataset collected from Twitter. Our experimental results show that our algorithm measures user influence better by way of a user recommendation task, where our algorithm outperforms TwitterRank across a range of experimental network settings.

Original language	English
Title of host publication	WWW '20
Subtitle of host publication	Companion Proceedings of the Web Conference 2020
Editors	Amal El Fallah Seghrouchni, Gita Sukthankar, Tie-Yan Liu, Maarten van Steen
Place of Publication	New York
Publisher	Association for Computing Machinery (ACM)
Pages	379-384
Number of pages	6
ISBN (Print)	978-1-4503-7024-0
DOIs	https://doi.org/10.1145/3366424.3383299
Publication status	Published - 1 Apr 2020
Event	4th International Workshop on Mining Actionable Insights from Social Networks - Taipei, Taiwan Duration: 20 Apr 2020 → 24 Apr 2020 Conference number: 4 https://www.maisonworkshop.org/

Workshop

Workshop	4th International Workshop on Mining Actionable Insights from Social Networks
Abbreviated title	MAISoN 2020
Country/Territory	Taiwan
City	Taipei
Period	20/04/20 → 24/04/20
Internet address	https://www.maisonworkshop.org/

Access to Document

10.1145/3366424.3383299

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Association for Computing Machinery at https://dl.acm.org/doi/10.1145/3366424.3383299 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 712 KB

Handle.net

Persistent link

Cite this

Bo, H., McConville, R., Hong, J., & Liu, W. (2020). Social Network Influence Ranking via Embedding Network Interactions for User Recommendation. In A. E. F. Seghrouchni, G. Sukthankar, T.-Y. Liu, & M. van Steen (Eds.), WWW '20: Companion Proceedings of the Web Conference 2020 (pp. 379-384). Association for Computing Machinery (ACM). https://doi.org/10.1145/3366424.3383299

@inproceedings{3b2ebb79ac944243bbbef8e1a859795a,

title = "Social Network Influence Ranking via Embedding Network Interactions for User Recommendation",

abstract = "Within social networks user influence may be modelled based on user interactions. Further, it is typical to recommend users to others. What is the role of user influence in user recommendation? In this paper, we first propose to use a node embedding approach to integrate many types of interaction into embedded spaces where we then define a novel closeness measure to quantify the closeness of users based on interactions. We then propose a new influence ranking algorithm based on PageRank by incorporating the closenessmeasure into the ranking mechanism. We evaluate our algorithm, EIRank, using a dataset collected from Twitter. Our experimental results show that our algorithm measures user influence better by way of a user recommendation task, where our algorithm outperforms TwitterRank across a range of experimental network settings.",

author = "Hongbo Bo and Ryan McConville and Jun Hong and Weiru Liu",

year = "2020",

month = apr,

day = "1",

doi = "10.1145/3366424.3383299",

language = "English",

isbn = " 978-1-4503-7024-0",

pages = "379--384",

editor = "Seghrouchni, {Amal El Fallah} and Gita Sukthankar and Tie-Yan Liu and {van Steen}, Maarten",

booktitle = "WWW '20",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "4th International Workshop on Mining Actionable Insights from Social Networks, MAISoN 2020 ; Conference date: 20-04-2020 Through 24-04-2020",

url = "https://www.maisonworkshop.org/",

}

Bo, H , McConville, R, Hong, J & Liu, W 2020, Social Network Influence Ranking via Embedding Network Interactions for User Recommendation. in AEF Seghrouchni, G Sukthankar, T-Y Liu & M van Steen (eds), WWW '20: Companion Proceedings of the Web Conference 2020. Association for Computing Machinery (ACM), New York, pp. 379-384, 4th International Workshop on Mining Actionable Insights from Social Networks, Taipei, Taiwan, 20/04/20. https://doi.org/10.1145/3366424.3383299

Social Network Influence Ranking via Embedding Network Interactions for User Recommendation. / Bo, Hongbo ; McConville, Ryan; Hong, Jun et al.
WWW '20: Companion Proceedings of the Web Conference 2020. ed. / Amal El Fallah Seghrouchni; Gita Sukthankar; Tie-Yan Liu; Maarten van Steen. New York: Association for Computing Machinery (ACM), 2020. p. 379-384.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Social Network Influence Ranking via Embedding Network Interactions for User Recommendation

AU - Bo, Hongbo

AU - McConville, Ryan

AU - Hong, Jun

AU - Liu, Weiru

N1 - Conference code: 4

PY - 2020/4/1

Y1 - 2020/4/1

N2 - Within social networks user influence may be modelled based on user interactions. Further, it is typical to recommend users to others. What is the role of user influence in user recommendation? In this paper, we first propose to use a node embedding approach to integrate many types of interaction into embedded spaces where we then define a novel closeness measure to quantify the closeness of users based on interactions. We then propose a new influence ranking algorithm based on PageRank by incorporating the closenessmeasure into the ranking mechanism. We evaluate our algorithm, EIRank, using a dataset collected from Twitter. Our experimental results show that our algorithm measures user influence better by way of a user recommendation task, where our algorithm outperforms TwitterRank across a range of experimental network settings.

AB - Within social networks user influence may be modelled based on user interactions. Further, it is typical to recommend users to others. What is the role of user influence in user recommendation? In this paper, we first propose to use a node embedding approach to integrate many types of interaction into embedded spaces where we then define a novel closeness measure to quantify the closeness of users based on interactions. We then propose a new influence ranking algorithm based on PageRank by incorporating the closenessmeasure into the ranking mechanism. We evaluate our algorithm, EIRank, using a dataset collected from Twitter. Our experimental results show that our algorithm measures user influence better by way of a user recommendation task, where our algorithm outperforms TwitterRank across a range of experimental network settings.

U2 - 10.1145/3366424.3383299

DO - 10.1145/3366424.3383299

M3 - Conference Contribution (Conference Proceeding)

SN - 978-1-4503-7024-0

SP - 379

EP - 384

BT - WWW '20

A2 - Seghrouchni, Amal El Fallah

A2 - Sukthankar, Gita

A2 - Liu, Tie-Yan

A2 - van Steen, Maarten

PB - Association for Computing Machinery (ACM)

CY - New York

T2 - 4th International Workshop on Mining Actionable Insights from Social Networks

Y2 - 20 April 2020 through 24 April 2020

ER -

Social Network Influence Ranking via Embedding Network Interactions for User Recommendation

Abstract

Workshop

Access to Document

Handle.net

Fingerprint

Cite this