Received 15.12.2024, Revised 06.03.2025, Accepted 24.04.2025

Analysis of the impact of cross-platform behaviour on recommendation quality

Anton Pakula, Vladimir Garmash

The rapid growth in the number of digital platforms and the diversity of online services create new challenges for the development of recommender systems that must factor in cross-platform user behaviour to ensure the accuracy and privacy of recommendations. The purpose of this study was to determine how combining cross-platform behavioural data can improve the accuracy of recommender systems. To this end, the study analysed modern machine learning algorithms and Big Data processing methods that enable the efficient integration of information from various sources. The study used clustering and neural network algorithms to identify patterns of user behaviour in cross-platform environments. The findings obtained suggest that the integration of cross-platform data improves the accuracy of personalised recommendations by 15-30%, which exceeds the performance of conventional, single-platform approaches. Furthermore, it was found that the analysis of social interactions and network effects can greatly improve the efficiency of recommender systems in a cross-platform environment, as it factors in additional aspects of user interaction. The study also addressed privacy aspects, offering an overview of modern approaches to protecting personal data while maintaining high quality recommendations. Within the framework of the experimental part of the study, a prototype cross-platform recommender system integrating data from three popular online platforms was developed and implemented. Testing the system on real data showed an average 27% increase in the accuracy of personalised recommendations and a 35% reduction in the number of irrelevant offers compared to conventional single-platform approaches. Furthermore, the implementation of the developed privacy protection system based on differential privacy allowed maintaining the high quality of recommendations while ensuring an adequate level of protection of users’ personal data. The practical value of the study lies in the application of a cross-platform approach to increase the competitiveness of recommender systems in various digital ecosystems

data integration; content personalisation; data privacy; machine learning; user experience; recommendation algorithms; Big Data
30-41
Pakula, A., & Garmash, V. (2025). Analysis of the impact of cross-platform behaviour on recommendation quality. Information Technologies and Computer Engineering, 22(1), 30-41. https://doi.org/10.63341/vitce/1.2025.30

References

[1] Aliiev, R.N. (2024). Development of a personalized content recommendation system for streaming platform based on user behavior analysis. (Bachelor’s Thesis, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine).

[2] Asad, M., Shaukat, S., Javanmardi, E., Nakazato, J., & Tsukada, M. (2023). A comprehensive survey on privacypreserving techniques in federated recommendation systems. Applied Sciences, 13(10), article number 6201. doi: 10.3390/app13106201.

[3] Boumhidi, A., & Benlahbib, A. (2021). Cross-platform reputation generation system based on aspect-based sentiment analysis. IEEE Access, 10, 2515-2531. doi: 10.1109/ACCESS.2021.3139956.

[4] Cao, D., Nie, L., He, X., Wei, X., Hu, X., Wu, S., & Chua, T. S. (2017). Cross-platform app recommendation by jointly modeling ratings and texts. ACM Transactions on Information Systems (TOIS), 35(4), 1-27. doi: 10.1145/3017429.

[5] Chen, M. (2020). Implementation and usability testing of a cross-platform mood-based video recommender system for older adults. (Doctoral dissertation, University of Toronto, Toronto, Canada).

[6] Deng, Z., Sang, J., & Xu, C. (2013). Personalized video recommendation based on cross-platform user modeling. In 2013 IEEE International conference on multimedia and expo (ICME) (pp. 1-6). San Josed: IEEE. doi: 10.1109/ ICME.2013.6607513.

[7] Drobot, A.Y. (2022). Development of a cross-platform image search system web application using ASP.NET technology. (Bachelor’s Thesis, Dnipro University of Technology, Dnipro, Ukraine).

[8] Du, H., Zhang, Y., Gang, K., Zhang, L., & Chen, Y. C. (2021). Online ensemble learning algorithm for imbalanced data stream. Applied Soft Computing, 107, article number 107378. doi: 10.1016/j.asoc.2021.107378.

[9] Huang, N., Zhang, S., Wan, D., Que, T., & Yu, P.S. (2023). Cross-platform sequential recommendation with sharing item-level relevance data. Information Sciences, 621, 265-286. doi: 10.1016/j.ins.2022.11.112.

[10] Ke, G., Du, H.L., & Chen, Y.C. (2021). Cross-platform dynamic goods recommendation system based on reinforcement learning and social networks. Applied Soft Computing, 104, article number 107213. doi: 10.1016/j. asoc.2021.107213.

[11] Krijestorac, H., Garg, R., & Mahajan, V. (2020). Cross-platform spillover effects in consumption of viral content: A quasi-experimental analysis using synthetic controls. Information Systems Research, 31(2), 449-472. doi: 10.1287/ isre.2019.0897.

[12] Li, M., Wang, Y., Xin, Y., Zhu, H., Tang, Q., Chen, Y., Yang, Y. & Yang, G. (2021). Cross-platform strong privacy protection mechanism for review publication. Security and Communication Networks, 2021(1), article number 5556155. doi: 10.1155/2021/5556155.

[13] Liu, Q., Zhang, X., Zhang, L., & Zhao, Y. (2019). The interaction effects of information cascades, word of mouth and recommendation systems on online reading behavior: An empirical investigation. Electronic Commerce Research, 19, 521-547. doi: 10.1007/s10660-018-9312-0.

[14] Murić, G., Tregubov, A., Blythe, J., Abeliuk, A., Choudhary, D., Lerman, K., & Ferrara, E. (2020). Massive cross-platform simulations of online social networks. In Proceedings of the 19th international conference on autonomous agents and multiagent systems (pp. 895-903). Auckland: AAMAS.

[15] Segun-Falade, O.D., Osundare, O.S., Kedi, W.E., Okeleke, P.A., Ijomah, T.I., & Abdul-Azeez, O.Y. (2024). Developing cross-platform software applications to enhance compatibility across devices and systems. Computer Science & IT Research Journal, 5(8). doi: 10.51594/csitrj.v5i8.1491.

[16] Shin, D.H. (2016). Cross-platform users’ experiences toward designing interusable systems. International Journal of Human-Computer Interaction, 32(7), 503-514. doi: 10.1080/10447318.2016.1177277.

[17] Suhas, G.K., Devananda, S.N., Jagadeesh, R., Pareek, P.K., & Dixit, S. (2021). Recommendation-based interactivity through cross platform using Big Data. In J.M.R.S. Tavares, S. Chakrabarti, A. Bhattacharya & S. Ghatak (Eds.), Emerging technologies in data mining and information security. Lecture notes in networks and systems (Vol. 164, pp. 651659). Singapore: Springer. doi: 10.1007/978-981-15-9774-9_60.

[18] Sun, Z., Wang, Z., & Xu, Y. (2023). Privacy protection in cross-platform recommender systems: Techniques and challenges. Wireless Netw, 30, 6721-6730. doi: 10.1007/s11276-023-03509-z.

[19] Zeng, J., Huang, Z., Wu, Z., Chen, Z., & Chen, Y. (2024). FedGR: Cross-platform federated group recommendation system with hypergraph neural networks. Journal of Intelligent Information Systems. doi: 10.1007/s10844-024-00887-4.

[20] Zhang, X., & Yu, X. (2020). The impact of perceived risk on consumers’ cross-platform buying behavior. Frontiers in Psychology, 11. doi: 10.3389/fpsyg.2020.592246.