A deep neural network-based approach in tag recommender system to overcome users' Cold Start

Document Type : Research Paper

Authors

1 Department of Computer and Information Technology Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

2 Faculty of Information Technology, ICT Research Institute (Iran Telecommunication Research Center), Tehran, Iran

Abstract

Recommender systems are used in various fields such as movies, music, and social networks. Recommender systems aim to provide attractive offers to users according to their performance in the system. The most popular recommender systems are content-based models and collaborative filtering methods. One of the most important challenges and problems in recommender systems is the challenge of users' cold start. So far, various methods such as machine learning algorithms, optimization approaches, and statistical methods, have been proposed by other researchers in improving internet marketing strategy and overcoming the cold-start problem, which despite having numerous applications, still could not solve the start problem. This article will investigate the problem of cold start users' by presenting a recommendation model based on a deep neural network and considering the problem of improving the internet (network) marketing strategy. In this article, the relevant simulation is done on the popular Movielens dataset, which is from 2015, and the evaluations of the methods presented on this dataset are compared

Keywords

[1] D L. Abd Al-Nabi and S Sh. Ahmed, Deep learning for big weather data analyzing and forecasting, Int. J. Nonlinear Anal. Appl. In Press (2023), doi: 10.22075/ijnaa.2023.30013.4313.
[2] F.M. Belem, A.G. Heringer, J.M. Almeida, and M.A. Goncalves, Exploiting syntactic and neighbourhood attributes to address cold start in tag recommendation, Inf. Process. Manag. 56 (2019), no. 3, 771–790.
[3] B. Doucoure, K. Agbossou, and A. Cardenas, Time series prediction using artificial wavelet neural network and multi-resolution analysis: Application to wind speed data, Renewable Energy 92 (2016), 202–211.
[4] T. Ebesu and Y. Fang, Neural semantic personalized ranking for item cold-start recommendation, Inf. Retriev. J. 20 (2017), no. 2, 109–131.
[5] M. Fadavi Amiri, M. Hosseinzadeh, and S.M.R. Hashemi, Improving image segmentation using artificial neural networks and evolutionary algorithms, Int. J. Nonlinear Anal. Appl. In Press (2023), doi:10.22075/ijnaa.2023.30232.4371.
[6] F. Figueiredo, H. Pinto, F. Belem, J. Almeida, M. Goncalves, D. Fernandes, and E. Moura, Assessing the quality of textual features in social media, Inf. Process. Manag. 49 (2013), no. 1, 222–247.
[7] K.K. Fletcher, A method for dealing with data sparsity and cold-start limitations in service recommendation using personalized preferences, 2017 IEEE Int. Conf. Cogn. Comput. (ICCC) (Honolulu, HI, USA), IEEE, June 2017, pp. 72–79.
[8] A. Ghanbari Sorkhi, M. Iranpour Mobarakeh, S.M.R. Hashemi, and M. Faridpour, Predicting drug-target interaction based on bilateral local models using a decision tree-based hybrid support vector machine, Int. J. Nonlinear Anal. Appl. 12 (2021), no. 2, 135–144.
[9] I. Guy, N. Zwerdling, I. Ronen, D. Carmel, and E. Uziel, Social media recommendation based on people and tags, Proc. 33rd Int. ACM SIGIR Conf. Res. Dev. Inf. Retriev., 2010, pp. 194–201.
[10] M.-H. Hsu and H.-H. Chen, Efficient and effective prediction of social tags to enhance web search, J. Amer. Soc. Inf. Sci. Technol. 62 (2011), no. 8, 1473–1487.
[11] K. Lei, Q. Fu, M. Yang, and Y. Liang, Tag recommendation by text classification with attention-based capsule network, Neurocomputing 391 (2020), 65–73.
[12] X. Li, L. Guo, and Y.E. Zhao, Tag-based social interest discovery, Proc. 17th Int. Conf. World Wide Web, 2008, pp. 675–684.
[13] B. Lika, K. Kolomvatsos, and S. Hadjiefthymiades, Facing the cold start problem in recommender systems, Expert Syst. Appl. 41 (2014), no. 4, 2065–2073.
[14] C.-H. Lin and H. Chi, A novel movie recommendation system based on collaborative filtering and neural networks, Adv. Inf. Network. Appl.: Proc. 33rd Int. Conf. Adv. Inf. Network. Appl. (AINA-2019) 33, Springer, 2020, 895–903.
[15] W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F.E. Alsaadi, A survey of deep neural network architectures and their applications, Neurocomputing 234 (2017), 11–26.
[16] L. Luo, H. Xie, Y. Rao, and F.L. Wang, Personalized recommendation by matrix co-factorization with tags and time information, Expert Syst. Appl. 119 (2019), 311–321.
[17] M.A. Masood, R.A. Abbasi, O. Maqbool, M. Mushtaq, N.R. Aljohani, A. Daud, M.A. Aslam, and J.S. Alowibdi, MFS-LDA: A multi-feature space tag recommendation model for cold start problem, Program 51 (2017), no. 3, 218–234.
[18] V. Oliveira, G. Gomes, F. Belem, W. Brandao, J. Almeida, N. Ziviani, and M. Goncalves, Automatic query expansion based on tag recommendation, Proc. 21st ACM Int. Conf. Inf. Knowledge Manag., 2012, pp. 1985–1989.
[19] A. Tejeda-Lorente, J. Bernabe-Moreno, C. Porcel, and E. Herrera-Viedma, Using Bibliometrics and Fuzzy Linguistic Modeling to Deal with Cold Start in Recommender Systems for Digital Libraries, Advances in Fuzzy Logic and Technology 2017 (Janusz Kacprzyk, Eulalia Szmidt, Slawomir Zadrozny, Krassimir T. Atanassov, and Maciej Krawczak, eds.), vol. 643, Springer International Publishing, Cham, 2018, Series Title: Advances in Intelligent Systems and Computing, pp. 393–404.
[20] Ma. Volkovs, G.W. Yu, and T. Poutanen, Content-based neighbor models for Cold Start in Recommender Systems, Proc. Recomm. Syst. Challenge 2017 (Como Italy), ACM, August 2017, pp. 1–6.
[21] L. Wang, Ch. Wang, K. Wang, and X. He, BiUCB: A contextual bandit algorithm for cold-start and diversified recommendation, IEEE Int. Conf. Big Knowledge (ICBK) (Hefei, China), IEEE, 2017, pp. 248–253.
[22] J. Wei, J. He, K. Chen, Y. Zhou, and Z. Tang, Collaborative filtering and deep learning based recommendation system for cold start items, Expert Syst. Appl. 69 (2017), 29–39.
[23] Y. Wu, S. Xi, Y. Yao, F. Xu, H. Tong, and J. Lu, Guiding supervised topic modeling for content based tag recommendation, Neurocomputing 314 (2018), 479–489.
[24] Q. Xie, F. Xiong, T. Han, Y. Liu, L. Li, and Z. Bao, Interactive resource recommendation algorithm based on tag information, World Wide Web 21 (2018), 1655–1673.
[25] Z. Xu, D. Yuan, T. Lukasiewicz, Ch. Chen, Y. Miao, and G. Xu, Hybrid deep-semantic matrix factorization for tag-aware personalized recommendation, ICASSP 2020-2020 IEEE Int. Conf. Acoustics Speech Signal Process. (ICASSP), IEEE, 2020, pp. 3442–3446.
[26] H. Yu, B. Zhou, M. Deng, and F. Hu, Tag recommendation method in folksonomy based on user tagging status, J. Intell. Inf. Syst. 50 (2018), 479–500.
[27] X. Zhou, J. He, G. Huang, and Y. Zhang, SVD-based incremental approaches for recommender systems, J. Comput. Syst. Sci. 81 (2015), no. 4, 717–733.
Volume 15, Issue 7
July 2024
Pages 197-214
  • Receive Date: 20 March 2023
  • Revise Date: 08 June 2023
  • Accept Date: 07 July 2023