A physics-informed neural network model for social media user growth

Lingju Kong; Ryan Z. Shi; Min Wang; Lingju Kong; Ryan Z. Shi; Min Wang

doi:10.3934/aci.2024012

Applied Computing and Intelligence

2024, Volume 4, Issue 2: 195-208. doi: 10.3934/aci.2024012

Previous Article Next Article

Research article

A physics-informed neural network model for social media user growth

1.
Department of Mathematics, University of Tennessee at Chattanooga, Chattanooga, TN 37403, USA
2.
Menaul School Qingdao, Qingdao 266000, China
3.
Department of Mathematics, Kennesaw State University, Marietta, GA 30060, USA

Received: 24 August 2024 Revised: 11 November 2024 Accepted: 13 November 2024 Published: 18 November 2024

In this paper, a physics-informed neural network model is proposed to predict the growth of online social network users. The number of online social network users is modeled by a stochastic process and the associated Kolmogorov forward equation is derived. Then, a physics-informed neural network model is built based on the Kolmogorov forward equation and trained using real-world data. By combining mathematical modeling with machine learning, our approach provides a practical and interpretable methodology that harnesses the strengths of both physical laws and advancements in machine learning, while minimizing the opacity in machine learning models.
- physics-informed neural network,
- Kolmogorov forward equations,
- online social networks,
- compartment models,
- Markov process
Citation: Lingju Kong, Ryan Z. Shi, Min Wang. A physics-informed neural network model for social media user growth[J]. Applied Computing and Intelligence, 2024, 4(2): 195-208. doi: 10.3934/aci.2024012

Related Papers:

Abstract

In this paper, a physics-informed neural network model is proposed to predict the growth of online social network users. The number of online social network users is modeled by a stochastic process and the associated Kolmogorov forward equation is derived. Then, a physics-informed neural network model is built based on the Kolmogorov forward equation and trained using real-world data. By combining mathematical modeling with machine learning, our approach provides a practical and interpretable methodology that harnesses the strengths of both physical laws and advancements in machine learning, while minimizing the opacity in machine learning models.

References

[1]	E. Allen, Modeling with Itô stochastic differential equations, Dordrecht: Springer, 2007. http://dx.doi.org/10.1007/978-1-4020-5953-7
[2]	T. Boyle, R. Aygun, Kennesaw State University HPC facilities and resources, Digital Commons Training Materials, 10 (2021), 1–3.
[3]	F. Brauer, Mathematical epidemiology: past, present, and future, Infectious Disease Modelling, 2 (2017), 113–127. http://dx.doi.org/10.1016/j.idm.2017.02.001 doi: 10.1016/j.idm.2017.02.001
[4]	C. Browne, M. Wang, G. F. Webb, A stochastic model of nosocomial epidemics in hospital intensive care units, Electron. J. Qual. Theory Differ. Equ., 2017 (2017), 1–12. http://dx.doi.org/10.14232/ejqtde.2017.1.6 doi: 10.14232/ejqtde.2017.1.6
[5]	J. Cannarella, J. Spechler, Epidemiological modeling of online network dynamics, arXiv: 1401.4208. http://dx.doi.org/10.48550/arXiv.1401.4208
[6]	R. Chen, L. Kong, M. Wang, Stability analysis of an online social network model, Rocky Mountain J. Math., 53 (2023), 1019–1041. http://dx.doi.org/10.1216/rmj.2023.53.1019 doi: 10.1216/rmj.2023.53.1019
[7]	S. Chen, J. Shi, Z. Shuai, Y. Wu, Evolution of dispersal in advective patchy environments, J. Nonlinear Sci., 33 (2023), 40. http://dx.doi.org/10.1007/s00332-023-09899-w doi: 10.1007/s00332-023-09899-w
[8]	S. Cuomo, V. S. Di Cola, F. Giampaolo, G. Rozza, M. Raissi, F. Piccialli, Scientific machine learning through physics-informed neural networks: where we are and what's next, J. Sci. Comput., 92 (2022), 88. http://dx.doi.org/10.1007/s10915-022-01939-z doi: 10.1007/s10915-022-01939-z
[9]	D. Gao, X. Yuan, A hybrid Lagrangian-Eulerian model for vector-borne diseases, J. Math. Biol., 89 (2024), 16. http://dx.doi.org/10.1007/s00285-024-02109-5 doi: 10.1007/s00285-024-02109-5
[10]	J. R. Graef, S. Ho, L. Kong, M. Wang, A fractional differential equation model for bike share systems, J. Nonlinear Funct. Anal., 2019 (2019), 23. http://dx.doi.org/10.23952/jnfa.2019.23 doi: 10.23952/jnfa.2019.23
[11]	J. R. Graef, L. Kong, A. Ledoan, M. Wang, Stability analysis of a fractional online social network model, Math. Comput. Simulat., 178 (2020), 625–645. http://dx.doi.org/10.1016/j.matcom.2020.07.012 doi: 10.1016/j.matcom.2020.07.012
[12]	Z. Hao, S. Liu, Y. Zhang, C. Ying, Y. Feng, H. Su, et al., Physics-informed machine learning: a survey on problems, methods and applications, arXiv: 2211.08064. http://dx.doi.org/10.48550/arXiv.2211.08064
[13]	D. P. Kingma, J. Ba, Adam: a method for stochastic optimization, arXiv: 1412.6980. http://dx.doi.org/10.48550/arXiv.1412.6980
[14]	N. Kimmel, L. Kong, M. Wang, Modeling the dynamics of user adoption and abandonment in online social networks, Math. Method. Appl. Sci., in press. http://dx.doi.org/10.1002/mma.10413
[15]	D. Kincaid, W. Cheney, Numerical analysis: mathematics of scientific computing, 3 Eds., Providence: American Mathematical Society, 2002.
[16]	L. Kong, Modelling the dynamics of product adoption and abandonment, Proc. R. Soc. A., 480 (2024), 20240034. http://dx.doi.org/10.1098/rspa.2024.0034 doi: 10.1098/rspa.2024.0034
[17]	L. Kong, M. Wang, Deterministic and stochastic online social network models with varying population size, Dynamics of Continuous, Discrete and Impulsive Systems Series A: Mathematical Analysis, 30 (2023), 253–275.
[18]	L. Kong, M. Wang, Optimal control for an ordinary differential equation online social network model, Differ. Equat. Appl., 14 (2022), 205–214.
[19]	B. Ma, C. Li, J. Warner, Structured mathematical models to investigate the interactions between Plasmodium falciparum malaria parasites and host immune response, Math. Biosci., 310 (2019), 65–75. http://dx.doi.org/10.1016/j.mbs.2019.02.005 doi: 10.1016/j.mbs.2019.02.005
[20]	M. Mohsin, 10 social media statistics you need to know in 2024, Oberlo, 2024. Available from: https://www.oberlo.com/blog/social-media-marketing-statistics.
[21]	K. Nath, X. Meng, D. J. Smith, G. Karniadakis, Physics-informed neural networks for predicting gas flow dynamics and unknown parameters in diesel engines, Sci. Rep., 13 (2023), 13683. http://dx.doi.org/10.1038/s41598-023-39989-4 doi: 10.1038/s41598-023-39989-4
[22]	E. Ortiz-Ospina, The rise of social media, Our World In Data, 2019. Available from: https://ourworldindata.org/rise-of-social-media.
[23]	L. Wang, M. Wang, Stability and bifurcation analysis for an OSN model with delay, Advances in the Theory of Nonlinear Analysis and its Application, 7 (2023), 413–427. http://dx.doi.org/10.31197/atnaa.1152602 doi: 10.31197/atnaa.1152602
[24]	L. Wang, M. Wang, Bifurcation analysis for an OSN model with two delays, Mathematics, 12 (2024), 1321. http://dx.doi.org/10.3390/math12091321 doi: 10.3390/math12091321
[25]	G. Webb, X. E. Zhao, An epidemic model with infection age and vaccination age structure, Infect. Dis. Rep., 16 (2024), 35–64. http://dx.doi.org/10.3390/idr16010004 doi: 10.3390/idr16010004
[26]	B. Wong, Top social media statistics and trends of 2024, Forbes Media LLC., 2024. Available from: https://www.forbes.com/advisor/business/social-media-statistics/.
[27]	World bank open data, The World Bank Group, 2024. Available from: https://data.worldbank.org/indicator/SP.POP.TOTL.
[28]	N. Xiao, H. Xu, A. Morani, A. Shokri, H. Mukalazi, Exploring local and global stability of COVID-19 through numerical schemes, Sci. Rep., 14 (2024), 7960. http://dx.doi.org/10.1038/s41598-024-56938-x doi: 10.1038/s41598-024-56938-x

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)