Investigating the possibility of biasing recommendation algorithms from users' rating behavior in online social networks

Subject Areas : Computer Engineering and IT

Mehdi  Safarpour ¹ (Islamic Azad University Shiraz Branch)
Seyed Hadi  Yaghobian ² (Department of Computer Engineering Yasooj Branch, Islamic Azad University Yasooj, Iran)
Karamollah  BagheriFard ³ (Department of Computer Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran)
razieh  malekhoseini ⁴ (Assistant professor in architecture, Department of architecture and urban design, Shiraz Branch , Islamic Azad University, Shiraz , Iran)
Samad   Nejatian ⁵ (Department of Electrical Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran)

Received: 2023-12-10 Accepted : 2024-02-07 Published : 2024-04-02

Keywords: social networks, recommendation systems, collaborative filtering, users' behavior prediction ,

Abstract :

As online social networks become more widely used, there is a growing focus on the role of recommender algorithms within these platforms. It is important to assess the accuracy of these algorithms in providing suitable recommendations. Our research demonstrates that the presence of individuals and acquaintances within social networks influences user behavior in ways that are largely psychological. Many user actions on a post are influenced by their respect or closeness to the post's owner. This article explores how the predictability of user behavior towards posts from friends and acquaintances highlights the impact of emotional connections stemming from stable social relationships on post acceptance. It also raises concerns about the potential for incorrect recommendations in algorithms based on collaborative filtering due to data bias caused by these factors.

References:

[1] M. Yang, S. Zhang, H. Zhang, and J. Xia, “A new user behavior evaluation method in online social network,” J. Inf. Secur. Appl., vol. 47, pp. 217–222, 2019.#
[2] M. G. Campana and F. Delmastro, “Recommender systems for online and mobile social networks: A survey,” Online Soc. Netw. Media, vol. 3–4, pp. 75–97, 2017.#
[3] J.-H. Kang and K. Lerman, “LA-CTR: A limited attention collaborative topic regression for social media,” arXiv [cs.IR], 2013.#
[4] C. C. Aggarwal, Recommender Systems: The Textbook, 1st ed. Cham, Switzerland: Springer International Publishing, 2016.#
[5] F. C. T. Chua, H. W. Lauw, and E.-P. Lim, “Generative models for item adoptions using social correlation,” IEEE Trans. Knowl. Data Eng., vol. 25, no. 9, pp. 2036–2048, 2013.#
[6] N. D. Rodríguez, M. P. Cuéllar, J. Lilius, and M. D. Calvo-Flores, “A survey on ontologies for human behavior recognition,” ACM Comput. Surv., vol. 46, no. 4, pp. 1–33, 2014.#
[7] B. L. Bianca, “The user behavior analysis based on text messages using parafac and block term decomposition,” Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 10, 2018.#
[8] N. O. Hodas and K. Lerman, “How visibility and divided attention constrain social contagion,” arXiv [physics.soc-ph], 2012.#
[9] R. I. M. Dunbar and S. Shultz, “Evolution in the social brain,” Science, vol. 317, no. 5843, pp. 1344–1347, 2007.#
[10] G. Buscher, E. Cutrell, and M. R. Morris, “What do you see when you’re surfing?: Using eye tracking to predict salient regions of web pages,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2009.#
[11] M. Aivazoglou et al., “A fine-grained social network recommender system,” Soc. Netw. Anal. Min., vol. 10, no. 1, 2020.#
[12] D. Agarwal and B.-C. Chen, “fLDA: Matrix factorization through latent dirichlet allocation,” in Proceedings of the Third ACM International Conference on Web Search and Data Mining - WSDM ’10, 2010.#
[13] D. Bokde, S. Girase, and D. Mukhopadhyay, “Matrix factorization model in collaborative filtering algorithms: A survey,” Procedia Comput. Sci., vol. 49, pp. 136–146, 2015.#
[14] S. Purushotham, Y. Liu, and C.-C. J. Kuo, “Collaborative topic regression with social matrix factorization for recommendation systems,” arXiv [cs.IR], 2012.#
[15] Z. Sun et al., “Recommender systems based on social networks,” J. Syst. Softw., vol. 99, pp. 109–119, 2015.#
[16] Z. Li, F. Xiong, X. Wang, Z. Guan, and H. Chen, “Mining heterogeneous influence and indirect trust for recommendation,” IEEE Access, vol. 8, pp. 21282–21290, 2020.#
[17] W. Fan, Y. Ma, D. Yin, J. Wang, J. Tang, and Q. Li, “Deep social collaborative filtering,” in Proceedings of the 13th ACM Conference on Recommender Systems, 2019.#
[18] V. Arnaboldi, M. G. Campana, F. Delmastro, and E. Pagani, “PLIERS: A popularity-based recommender system for content dissemination in online social networks,” arXiv [cs.IR], 2023.#
[19] T. M. Newcomb, “Varieties of interpersonal attraction,” in Group dynamics: Research and theory, D. Cartwright and A. Zander, Eds. 1960, pp. 104–119.#
[20] G. L. Clore and D. Byrne, “A reinforcement-affect model of attraction,” in Foundations of Interpersonal Attraction, Elsevier, 1974, pp. 143–170.#
[21] M. McPherson, L. Smith-Lovin, and J. M. Cook, “Birds of a feather: Homophily in social networks,” Annu. Rev. Sociol., vol. 27, no. 1, pp. 415–444, 2001.#
[22] R. Hyon, A. M. Kleinbaum, and C. Parkinson, “Social network proximity predicts similar trajectories of psychological states: Evidence from multi-voxel spatiotemporal dynamics,” Neuroimage, vol. 216, no. 116492, p. 116492, 2020.#
[23] R. I. M. Dunbar, “Neocortex size as a constraint on group size in primates,” J. Hum. Evol., vol. 22, no. 6, pp. 469–493, 1992.#
[24] B. Gonçalves, N. Perra, and A. Vespignani, “Modeling users’ activity on twitter networks: Validation of dunbar’s number,” PLoS One, vol. 6, no. 8, p. e22656, 2011.#
[25] R. I. M. Dunbar, “Do online social media cut through the constraints that limit the size of offline social networks?,” R. Soc. Open Sci., vol. 3, no. 1, p. 150292, 2016.#
[26] H. Yin, B. Cui, L. Chen, Z. Hu, and Z. Huang, “A temporal context-aware model for user behavior modeling in social media systems,” in Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, 2014.#
[27] N. O. Hodas and K. Lerman, “How visibility and divided attention constrain social contagion,” in 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing, 2012.#
[28] R. I. M. Dunbar and S. Shultz, “Understanding primate brain evolution,” Philos. Trans. R. Soc. Lond. B Biol. Sci., vol. 362, no. 1480, pp. 649–658, 2007.#