Skip to content
Research Article Open access CC BY 4.0

Improving Business Pages Recommendation in Social Network Using Link Prediction Methods

Watare Asaph, Shaowei Sun

Asian Journal of Probability and Statistics · pp. 1–12 · Published 6 Aug 2021

10.9734/ajpas/2021/v14i230322

Abstract

Recently Social Network has become one of the favorite means for a modern society to perform social interaction and exchange information via the internet. Link prediction is a common problem that has broad application in such social networks, ranging from predicting unobserved interaction to recommending related items. In this paper, we investigate link recommendations over business pages on Facebook Social Network. More specifically, given a company in the network, we want to recommend potential companies to connect with. We start by introducing existing work in link recommendations and some link prediction models as our baseline. We then talk about the Graph Neural Network model SEAL to make a link recommendations in the network. Our results show that SEAL outperformed the compared baseline model while reaching above 94% Area Under Curve accuracy in link recommendations.

Social network link prediction facebook pages graph neural network

References (26)

  1. 1 LIBLINEAR: A Library for Large Linear Classification
  2. 2 Assortative Mixing in Networks [DOI]
  3. 3 LINE [DOI]
  4. 4 A New Status Index Derived from Sociometric Analysis [DOI]
  5. 5 The link‐prediction problem for social networks [DOI]
  6. 6 Friends and neighbors on the Web [DOI]
  7. 7 The Network Data Repository with Interactive Graph Analytics and Visualization [DOI]
  8. 8 Clustering and preferential attachment in growing networks [DOI]
  9. 9 Predicting missing links via local information [DOI]
  10. 10 Identifying Resilient Communities in Road Networks: A Path-Based Embedding Approach [DOI]
  11. 11 An End-to-End Deep Learning Architecture for Graph Classification [DOI]
  12. 12 Reprint of: The anatomy of a large-scale hypertextual web search engine [DOI]
  13. 13 Applications of link prediction in social networks: A review [DOI]
  14. 14 Link Prediction and Recommendation across Heterogeneous Social Networks [DOI]
  15. 15 Weisfeiler-Lehman Neural Machine for Link Prediction [DOI]
  16. 16 Fast and accurate link prediction in social networking systems [DOI]
  17. 17 Reducing the Rank in Relational Factorization Models by Including Observable Patterns
  18. 18 Efficient Latent Link Recommendation in Signed Networks [DOI]
  19. 19 Recommender Systems for Online and Mobile Social Networks: A survey [DOI]
  20. 20 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [DOI]
  21. 21 Journal of the American Society for Information Science and Technology [DOI]
  22. 22 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [DOI]
  23. 23 Mixed membership stochastic blockmodels [DOI]
  24. 24 Supervised Random Walks: Predicting and Recommending Links in Social Networks [DOI]
  25. 25 Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
  26. 26 The Impact of Facebook Fan Page Participation on Customer Behavior: An Empirical Investigation [DOI]

Cited by 2

The Effect of Link Recommendation Algorithms on Network Centrality Disparities

Timo Debono, Fernando P. Santos · Springer Proceedings in Complexity · 2023

Showing 1 of 2 known citations — external sources report more than can currently be individually listed.

Related research

Article metrics

Real usage data collected on this platform.

32

Page views

0

PDF downloads

2

Outbound clicks

2

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.