In recent years, the vigorous development of the Internet has led to the exponential growth of network information. The recommendation system can analyze the potential preferences of users according to their historical behavior data and provide personalized recommendations for users. In this study, the social network model was used for modeling, and the recommendation model was improved based on variational modal decomposition and the whale optimization algorithm. The generalized regression neural network structure and joint probability density function were used for sequencing and optimization, and then the genetic bat population optimization algorithm was used to solve the proposed algorithm. An intelligent recommendation algorithm for social networks based on improved generalized regression neural networks (RA-GNN) was proposed. In this study, three kinds of social network data sets obtained by real crawlers were used to solve the proposed RA-GNN algorithm in the real social network data environment. The experimental results showed that the RA-GNN algorithm proposed in this paper could implement efficient and accurate recommendations for social network information.
Citation: Gongcai Wu. Intelligent recommendation algorithm for social networks based on improving a generalized regression neural network[J]. Electronic Research Archive, 2024, 32(7): 4378-4397. doi: 10.3934/era.2024197
In recent years, the vigorous development of the Internet has led to the exponential growth of network information. The recommendation system can analyze the potential preferences of users according to their historical behavior data and provide personalized recommendations for users. In this study, the social network model was used for modeling, and the recommendation model was improved based on variational modal decomposition and the whale optimization algorithm. The generalized regression neural network structure and joint probability density function were used for sequencing and optimization, and then the genetic bat population optimization algorithm was used to solve the proposed algorithm. An intelligent recommendation algorithm for social networks based on improved generalized regression neural networks (RA-GNN) was proposed. In this study, three kinds of social network data sets obtained by real crawlers were used to solve the proposed RA-GNN algorithm in the real social network data environment. The experimental results showed that the RA-GNN algorithm proposed in this paper could implement efficient and accurate recommendations for social network information.
| [1] |
S. Ajmal, M. Awais, K. S. Khurshid, M. Shoaib, A. Abdelrahman, Data mining-based recommendation system using social networks-an analytical study, PeerJ Comput. Sci., 9 (2023), e1202. https://doi.org/10.7717/peerj-cs.1202 doi: 10.7717/peerj-cs.1202
|
| [2] |
A. Jokić, S. Baraković, J. B. Husić, J. Pleho, Partial rule security information and event management concept in detecting cyber incidents, Int. J. Secur. Netw., 16 (2021), 117–128. https://doi.org/10.1504/IJSN.2021.116777 doi: 10.1504/IJSN.2021.116777
|
| [3] |
Y. Yu, W. Qian, L. Zhang, R. Gao, A graph-neural-network-based social network recommendation algorithm using high-order neighbor information, Sensors, 22 (2022), 7122. https://doi.org/10.3390/s22197122 doi: 10.3390/s22197122
|
| [4] |
B. Lyes, A. Mourad, A. Djamil, A. Sofiane, P2PCF: A collaborative filtering based recommender system for peer to peer social networks, J. High Speed Networks, 27 (2021), 13–31. https://doi.org/10.3233/JHS-210649 doi: 10.3233/JHS-210649
|
| [5] |
F. Li, K. Wei, Study on social network recommendation service method based on mobile cloud computing, Int. J. Auton. Adapt. Commun. Syst., 14 (2021), 3983–408. https://doi.org/10.1504/IJAACS.2021.119124 doi: 10.1504/IJAACS.2021.119124
|
| [6] |
E. Rajalakshmi, V. Subramaniyaswamy, V. Vijayakumar, L. Ravi, Location‐based social network recommendations with computational intelligence‐based similarity computation and user check‐in behavior, Concurrency Comput. Pract. Exper., 33 (2021), e6106. https://doi.org/10.1002/cpe.6106 doi: 10.1002/cpe.6106
|
| [7] |
S. P. Perumal, G. Sannasi, K. Arputharaj, FIRMACA-Fuzzy intelligent recommendation model using ant clustering algorithm for social networking, SN Appl. Sci., 2 (2020), 1704. https://doi.org/10.1007/s42452-020-03486-4 doi: 10.1007/s42452-020-03486-4
|
| [8] |
R. Chen, Y. Chang, Q. Hua, Q. Gao, X. Ji, B. Wang, An enhanced social matrix factorization model for recommendation based on social networks using social interaction factors, Multimedia Tools Appl., 79 (2020), 14147–14177. https://doi.org/10.1007/s11042-020-08620-3 doi: 10.1007/s11042-020-08620-3
|
| [9] |
A. Ghorbel, M. Ghorbel, M. Jmaiel, A model-based approach for multi-level privacy policies derivation for cloud services, Int. J. Secur. Netw., 16 (2021), 12–27. https://doi.org/10.1504/IJSN.2021.112836 doi: 10.1504/IJSN.2021.112836
|
| [10] |
M. E. A. A. Tharwat, D. W. Jacob, M. F. M. Fudzee, S. Kasim, A. A. Ramli, M. Lubis, The role of trust to enhance the recommendation system based on social network, Int. J. Adv. Sci. Eng. Inf. Technol., 10 (2020), 1387–1395. https://doi.org/10.18517/ijaseit.10.4.10883 doi: 10.18517/ijaseit.10.4.10883
|
| [11] |
A. Khaled, S. Ouchani, C. Chohra, Recommendations-based on semantic analysis of social networks in learning environments, Comput. Hum. Behav., 101 (2019), 435–449. https://doi.org/10.1016/j.chb.2018.08.051 doi: 10.1016/j.chb.2018.08.051
|
| [12] |
M. Aivazoglou, A. O. Roussos, D. Margaris, C. Vassilakis, S. Ioannidis, J. Polakis, et al., A fine-grained social network recommender system, Social Network Anal. Min., 10 (2019), 8. https://doi.org/10.1007/s13278-019-0621-7 doi: 10.1007/s13278-019-0621-7
|
| [13] | S. Bedda, O. Kraa, M. Mohammedi, D. E. Zabia, I. Tegani, M. K. Benbraika, Optimization of passivity-based controller for a hybrid vehicle power source using the gray wolf algorithm, in 2024 8th International Conference on Image and Signal Processing and their Applications (ISPA), Biskra, Algeria, IEEE, (2024), 1–7. https://doi.org/10.1109/ISPA59904.2024.10536755 |
| [14] |
Z. Zhang, R. Sun, K. R. Choo, K. Fan, W. Wu, M. Zhang, et al., A novel social situation analytics-based recommendation algorithm for multimedia social networks, IEEE Access, 7 (2019), 117749–117760. https://doi.org/10.1109/ACCESS.2019.2934898 doi: 10.1109/ACCESS.2019.2934898
|
| [15] |
A. Zare, M. R. Motadel, A. Jalali, Presenting a hybrid model in social networks recommendation system architecture development, AI Soc., 35 (2019), 469–483. https://doi.org/10.1007/s00146-019-00893-z doi: 10.1007/s00146-019-00893-z
|
| [16] |
Z. Liu, H. Zhong, Study on tag, trust and probability matrix factorization based social network recommendation), KSII Trans. Internet Inf. Syst., 12 (2018), 2082–2102. https://doi.org/10.3837/tiis.2018.05.010 doi: 10.3837/tiis.2018.05.010
|
| [17] |
Z. Ding, X. Li, C. Jiang, M. Zhou, Objectives and state-of-the-art of location-based social network recommender systems, ACM Comput. Surv., 51 (2018), 1–28. https://doi.org/10.1145/3154526 doi: 10.1145/3154526
|
| [18] |
R. Jia, R. Li, M. Gao, Study on data sparsity in social network-based recommender system, Int. J. Comput. Sci. Eng., 20 (2019), 15–20. https://doi.org/10.1504/IJCSE.2019.103245 doi: 10.1504/IJCSE.2019.103245
|
| [19] |
X. Zhao, Z. Ma, Z. Zhang, A novel recommendation system in location-based social networks using distributed ELM, Memet. Comput., 10 (2018), 321–331. https://doi.org/10.1007/s12293-017-0227-4 doi: 10.1007/s12293-017-0227-4
|
| [20] |
S. Uribe, C. Ramirez, J. Finke, Recommender systems based on matrix factorization and the properties of inferred social networks, Discrete Math., Algorithms Appl., 16 (2024), 2350052. https://doi.org/10.1142/S1793830923500520 doi: 10.1142/S1793830923500520
|
| [21] |
C. Xu, A novel recommendation method based on social network using matrix factorization technique, Inf. Process. Manage., 54 (2018), 463–474. https://doi.org/10.1016/j.ipm.2018.02.005 doi: 10.1016/j.ipm.2018.02.005
|
| [22] |
D. Margaris, C. Vassilakis, P. Georgiadis, Recommendation information diffusion in social networks considering user influence and semantics, Social Network Anal. Min., 6 (2016), 108. https://doi.org/10.1007/s13278-016-0416-z doi: 10.1007/s13278-016-0416-z
|
| [23] |
P. Kefalas, P. Symeonidis, Y. Manolopoulos, Recommendations based on a heterogeneous spatio-temporal social network, World Wide Web, 21 (2018), 345–371. https://doi.org/10.1007/s11280-017-0454-0 doi: 10.1007/s11280-017-0454-0
|
| [24] |
M. Eirinaki, J. Gao, I. Varlamis, K. Tserpes, Recommender systems for large-scale social networks: A review of challenges and solutions, Future Gener. Comput. Syst., 78 (2018), 413–418. https://doi.org/10.1016/j.future.2017.09.015 doi: 10.1016/j.future.2017.09.015
|
| [25] |
M. G. Campana, F. Delmastro, Recommender systems for online and mobile social networks: A survey, Online Social Networks Media, 3–4 (2017), 75–97. https://doi.org/10.1016/j.osnem.2017.10.005 doi: 10.1016/j.osnem.2017.10.005
|
| [26] |
Y. Wang, M. Ding, Z. Chen, L. Luo, Caching placement with recommendation systems for cache-enabled mobile social networks, IEEE Commun. Lett., 21 (2017), 2266–2269. https://doi.org/10.1109/LCOMM.2017.2705695 doi: 10.1109/LCOMM.2017.2705695
|
| [27] |
G. Rojas, I. Garrido, Toward a rapid development of social network-based recommender systems, IEEE Lat. Am. Trans., 15 (2017), 753–759. https://doi.org/10.1109/TLA.2017.7896404 doi: 10.1109/TLA.2017.7896404
|
| [28] |
E. A. Mohammed, N. Linge, Cloud based electronic program guide system with integrated social network recommendations, I. J. e-Educ., e-Bus., e-Manage. e-Learn., 7 (2017), 100–110. https://doi.org/10.17706/ijeeee.2017.7.2.100-110 doi: 10.17706/ijeeee.2017.7.2.100-110
|
| [29] |
T. Li, M. Zhao, A. Liu, C. Huang, On selecting vehicles as recommenders for vehicular social networks, IEEE Access, 5 (2017), 5539–5555. https://doi.org/10.1109/ACCESS.2017.2678512 doi: 10.1109/ACCESS.2017.2678512
|
| [30] |
L. Luo, J. Dong, W. Kong, Y. Lu, Q. Zhang, Short-term probabilistic load forecasting using quantile regression neural network with accumulated hidden layer connection structure, IEEE Trans. Ind. Inf., 20 (2024), 5818–5828. https://doi.org/10.1109/TII.2023.3341242 doi: 10.1109/TII.2023.3341242
|
| [31] |
Y. Zhang, X. Li, Y. Zhang, A novel integrated optimization model for carbon emission prediction: A case study on the group of 20, J. Environ. Manage., 344 (2023), 118422. https://doi.org/10.1016/j.jenvman.2023.118422 doi: 10.1016/j.jenvman.2023.118422
|
| [32] |
L. S. Kullappa, R. A. Kumar, R. Kullappa, A study on recommendation systems in location based social networking, J. Inf. Optim. Sci., 41 (2017), 213–229. https://doi.org/10.31341/jios.41.2.6 doi: 10.31341/jios.41.2.6
|
| [33] |
C. Zhao, S. Sun, L. Han, Q. Peng, Hybrid matrix factorization for recommender systems in social networks, Neural Network World, 26 (2016) 559–569. https://doi.org/10.14311/NNW.2016.26.032 doi: 10.14311/NNW.2016.26.032
|
| [34] |
D. Margaris, C. Vassilakis, Exploiting rating abstention intervals for addressing concept drift in social network recommender systems, Informatics, 5 (2018), 21. https://doi.org/10.3390/informatics5020021 doi: 10.3390/informatics5020021
|
| [35] |
M. A. Zharova, V. I. Tsurkov, Neural network approaches for recommender systems, J. Comput. Syst. Sci. Int., 62 (2023), 1048–1062. https://doi.org/10.1134/S1064230723060126 doi: 10.1134/S1064230723060126
|
| [36] |
H. Li, X. Ma, J. Shi, Incorporating trust relation with PMF to enhance social network recommendation performance, Int. J. Pattern Recognit Artif Intell., 30 (2016), 1659016. https://doi.org/10.1142/S0218001416590163 doi: 10.1142/S0218001416590163
|
Gongcai Wu. Intelligent recommendation algorithm for social networks based on improving a generalized regression neural network[J]. Electronic Research Archive, 2024, 32(7): 4378-4397. doi: 10.3934/era.2024197
DownLoad: