Online social network user performance prediction by graph neural networks

(1) * Fail Gafarov Mail (Kazan Federal University, Russian Federation)
(2) Andrey Berdnikov Mail (Kazan Federal University, Russian Federation)
(3) Pavel Ustin Mail (Kazan Federal University, Russian Federation)
*corresponding author


Online social networks provide rich information that characterizes the user’s personality, his interests, hobbies, and reflects his current state. Users of social networks publish photos, posts, videos, audio, etc. every day. Online social networks (OSN) open up a wide range of research opportunities for scientists. Much research conducted in recent years using graph neural networks (GNN) has shown their advantages over conventional deep learning. In particular, the use of graph neural networks for online social network analysis seems to be the most suitable. In this article we studied the use of graph convolutional neural networks with different convolution layers (GCNConv, SAGEConv, GraphConv, GATConv, TransformerConv, GINConv) for predicting the user’s professional success in VKontakte online social network, based on data obtained from his profiles. We have used various parameters obtained from users’ personal pages in VKontakte social network (the number of friends, subscribers, interesting pages, etc.) as their features for determining the professional success, as well as networks (graphs) reflecting connections between users (followers/ friends). In this work we performed graph classification by using graph convolutional neural networks (with different types of convolution layers). The best accuracy of the graph convolutional neural network (0.88) was achieved by using the graph isomorphism network (GIN) layer. The results, obtained in this work, will serve for further studies of social success, based on metrics of personal profiles of OSN users and social graphs using neural network methods.


Online social network, graph neural networks, professional performance, graph convolutional neural networks, social graph



Article metrics

Abstract views : 111 | PDF views : 39




Full Text



[1] R. Buettner, “Predicting user behavior in electronic markets based on personality-mining in large online social networks,” Electron. Mark., vol. 27, no. 3, pp. 247–265, 2017, doi: 10.1007/s12525-016-0228-z.

[2] G. H. Martono, A. Azhari, and K. Mustofa, “An extended approach of weight collective influence graph for detection influence actor,” Int. J. Adv. Intell. Informatics, vol. 8, no. 1, pp. 1–11, Mar. 2022, doi: 10.26555/ijain.v8i1.800.

[3] A. Ulizulfa, R. Kusumaningrum, K. Khadijah, and R. Rismiyati, “Temperament detection based on Twitter data: classical machine learning versus deep learning,” Int. J. Adv. Intell. Informatics, vol. 8, no. 1, pp. 45–57, Mar. 2022, doi: 10.26555/ijain.v8i1.692.

[4] L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J. Big Data 2021 81, vol. 8, no. 1, pp. 1–74, Mar. 2021, doi: 10.1186/S40537-021-00444-8.

[5] F. J. P. Montalbo and A. A. Hernandez, “Classifying Barako coffee leaf diseases using deep convolutional models,” Int. J. Adv. Intell. Informatics, vol. 6, no. 2, pp. 197–209, Jul. 2020, doi: 10.26555/ijain.v6i2.495.

[6] J. Qiu, J. Tang, H. Ma, Y. Dong, K. Wang, and J. Tang, “DeepInf: Social influence prediction with deep learning,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., pp. 2110–2119, Jul. 2018, doi: 10.1145/3219819.3220077.

[7] L. Gao, H. Wang, Z. Zhang, H. Zhuang, and B. Zhou, “HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network,” Front. Phys., vol. 9, p. 729, Jan. 2022, doi: 10.3389/FPHY.2021.787185.

[8] L. Shang, Y. Zhang, D. Zhang, and D. Wang, “FauxWard: a graph neural network approach to fauxtography detection using social media comments,” Soc. Netw. Anal. Min., vol. 10, no. 1, pp. 1–16, Dec. 2020, doi: 10.1007/S13278-020-00689-W.

[9] P. Zhu et al., “SI-News: Integrating social information for news recommendation with attention-based graph convolutional network,” Neurocomputing, vol. 494, pp. 33–42, Jul. 2022, doi: 10.1016/J.NEUCOM.2022.04.073.

[10] C. Zhang, S. Wang, D. Zhan, M. Yin, and F. Lou, “Inferring Users’ Social Roles with a Multi-Level Graph Neural Network Model,” Entropy 2021, Vol. 23, Page 1453, vol. 23, no. 11, p. 1453, Nov. 2021, doi: 10.3390/E23111453.

[11] Q. Tan, N. Liu, and X. Hu, “Deep Representation Learning for Social Network Analysis,” Front. Big Data, vol. 2, p. 2, Apr. 2019, doi: 10.3389/FDATA.2019.00002.

[12] A. V. Mantzaris, D. Chiodini, and K. Ricketson, “Utilizing the simple graph convolutional neural network as a model for simulating influence spread in networks,” Comput. Soc. Networks, vol. 8, no. 1, pp. 1–17, Dec. 2021, doi: 10.1186/S40649-021-00095-Y.

[13] M. Zhang, Z. Cui, M. Neumann, and Y. Chen, “An End-to-End Deep Learning Architecture for Graph Classification,” Proc. AAAI Conf. Artif. Intell., vol. 32, no. 1, pp. 4438–4445, Apr. 2018, doi: 10.1609/AAAI.V32I1.11782.

[14] W. Fan et al., “Graph neural networks for social recommendation,” Web Conf. 2019 - Proc. World Wide Web Conf. WWW 2019, pp. 417–426, May 2019, doi: 10.1145/3308558.3313488.

[15] X. Wei, R. Yu, and J. Sun, “View-GCN: View-based graph convolutional network for 3D shape analysis,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 1847–1856, 2020, doi: 10.1109/CVPR42600.2020.00192.

[16] Y. Xie, M. Gong, Y. Gao, A. K. Qin, and X. Fan, “A Multi-Task Representation Learning Architecture for Enhanced Graph Classification,” Front. Neurosci., vol. 13, p. 1395, Jan. 2020, doi: 10.3389/FNINS.2019.01395.

[17] T. T. Mueller, J. C. Paetzold, C. Prabhakar, D. Usynin, D. Rueckert, and G. Kaissis, “Differentially Private Graph Classification with GNNs,” Feb. 2022, doi: 10.48550/arxiv.2202.02575.

[18] T. Le, M. Bertolini, F. Noé, and D. A. Clevert, “Parameterized Hypercomplex Graph Neural Networks for Graph Classification,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12893 LNCS, pp. 204–216, 2021, doi:10.48550/arXiv.2103.16584.

[19] D. Quercia, R. Lambiotte, D. Stillwell, M. Kosinski, and J. Crowcroft, “The personality of popular facebook users,” Proc. ACM Conf. Comput. Support. Coop. Work. CSCW, pp. 955–964, 2012, doi: 10.1145/2145204.2145346.

[20] M. Saqr, U. Fors, and J. Nouri, “Using social network analysis to understand online Problem-Based Learning and predict performance,” PLoS One, vol. 13, no. 9, p. e0203590, Sep. 2018, doi: 10.1371/JOURNAL.PONE.0203590.

[21] M. Saqr and A. Alamro, “The role of social network analysis as a learning analytics tool in online problem based learning,” BMC Med. Educ., vol. 19, no. 1, pp. 1–11, May 2019, doi: 10.1186/S12909-019-1599-6.

[22] A. M. Bhandarkar, A. K. Pandey, R. Nayak, K. Pujary, and A. Kumar, “Impact of social media on the academic performance of undergraduate medical students,” Med. J. Armed Forces India, vol. 77, pp. S37–S41, Feb. 2021, doi: 10.1016/J.MJAFI.2020.10.021.

[23] N. Melão and J. Reis, “Selecting talent using social networks: A mixed-methods study,” Heliyon, vol. 6, no. 4, p. e03723, Apr. 2020, doi: 10.1016/j.heliyon.2020.e03723.

[24] K. Toteva and E. Gourova, “Social network analysis in professional e-recruitment,” Adv. Intell. Soft Comput., vol. 101, pp. 75–80, 2011, doi: 10.1007/978-3-642-23163-6_11.

[25] S. Chala and M. Fathi, “Job seeker to vacancy matching using social network analysis,” Proc. IEEE Int. Conf. Ind. Technol., pp. 1250–1255, Apr. 2017, doi: 10.1109/ICIT.2017.7915542.

[26] F. M. Gafarov, K. S. Nikolaev, P. N. Ustin, A. A. Berdnikov, V. L. Zakharova, and S. A. Reznichenko, “A Complex Neural Network Model for Predicting a Personal Success based on their Activity in Social Networks,” Eurasia J. Math. Sci. Technol. Educ., vol. 17, no. 10, p. em2010, Aug. 2021, doi: 10.29333/EJMSTE/11175.

[27] E. Kay, J. A. Bondy, and U. S. R. Murty, “Graph Theory with Applications,” Oper. Res. Q., vol. 28, no. 1, p. 237, 1977, doi: 10.2307/3008805.

[28] P. Frasconi, M. Gori, and A. Sperduti, “A general framework for adaptive processing of data structures,” IEEE Trans. Neural Networks, vol. 9, no. 5, pp. 768–786, 1998, doi: 10.1109/72.712151.

[29] A. Sperduti and A. Starita, “Supervised neural networks for the classification of structures,” IEEE Trans. Neural Networks, vol. 8, no. 3, pp. 714–735, 1997, doi: 10.1109/72.572108.

[30] M. Gori, G. Monfardini, and F. Scarselli, “A new model for earning in raph domains,” Proc. Int. Jt. Conf. Neural Networks, vol. 2, pp. 729–734, 2005, doi: 10.1109/IJCNN.2005.1555942.

[31] F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neural network model,” IEEE Trans. Neural Networks, vol. 20, no. 1, pp. 61–80, Jan. 2009, doi: 10.1109/TNN.2008.2005605.

[32] “Convolutional networks on graphs for learning molecular fingerprints | Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2.” (accessed Jan. 02, 2020) doi : 10.48550/arXiv.1509.09292.

[33] J. Zhou et al., “Graph neural networks: A review of methods and applications,” AI Open, vol. 1, pp. 57–81, Jan. 2020, doi: 10.1016/J.AIOPEN.2021.01.001.

[34] D. Bacciu, F. Errica, A. Micheli, and M. Podda, “A gentle introduction to deep learning for graphs,” Neural Networks, vol. 129, pp. 203–221, Sep. 2020, doi: 10.1016/J.NEUNET.2020.06.006.

[35] Y. Zhou, H. Zheng, X. Huang, S. Hao, D. Li, and J. Zhao, “Graph Neural Networks: Taxonomy, Advances, and Trends,” ACM Trans. Intell. Syst. Technol., vol. 13, no. 1, Jan. 2022, doi: 10.1145/3495161.

[36] T. N. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” 5th Int. Conf. Learn. Represent. ICLR 2017 - Conf. Track Proc., Sep. 2016, doi : 10.48550/arXiv.1609.02907.

[37] N. K. Ahmed et al., “Inductive Representation Learning in Large Attributed Graphs,” no. Nips, pp. 1–11, 2017, [Online]. doi : 10.48550/arXiv.1710.09471.

[38] C. Morris et al., “Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks,” Proc. AAAI Conf. Artif. Intell., vol. 33, no. 01, pp. 4602–4609, Jul. 2019, doi: 10.1609/AAAI.V33I01.33014602.

[39] P. Veličković, A. Casanova, P. Liò, G. Cucurull, A. Romero, and Y. Bengio, “Graph Attention Networks,” 6th Int. Conf. Learn. Represent. ICLR 2018 - Conf. Track Proc., Oct. 2017, doi : 10.48550/arXiv.1710.10903.

[40] Y. Shi, Z. Huang, S. Feng, H. Zhong, W. Wang, and Y. Sun, “Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification,” IJCAI Int. Jt. Conf. Artif. Intell., vol. 2, pp. 1548–1554, Aug. 2021, doi: 10.24963/IJCAI.2021/214.

[41] K. Xu, S. Jegelka, W. Hu, and J. Leskovec, “How Powerful are Graph Neural Networks?,” 7th Int. Conf. Learn. Represent. ICLR 2019, Oct. 2018, doi : 10.48550/arXiv.1810.00826.

[42] P. E. Pope, S. Kolouri, M. Rostami, C. E. Martin, and H. Hoffmann, “Explainability methods for graph convolutional neural networks,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2019-June, pp. 10764–10773, Jun. 2019, doi: 10.1109/CVPR.2019.01103.

[43] H. Yuan, H. Yu, S. Gui, and S. Ji, “Explainability in Graph Neural Networks: A Taxonomic Survey,” IEEE Trans. Pattern Anal. Mach. Intell., Dec. 2020, doi : 10.48550/arXiv.2012.15445.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
E: (paper handling issues) (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0