A Systematic Review of AI Personalization for Data Privacy and Recommendation Quality

Firman Fauzi; Ade Permata  Surya; Harefan  Arief; Alifiah Ghaniyyu  Widyaningrum

doi:10.59395/ijadis.v7i2.1432

Authors

Firman Fauzi Faculty of Economic and Business, University of Mercubuana, Jakarta, Indonesia
Ade Permata Surya Faculty of Economic and Business, University of Mercubuana, Jakarta, Indonesia
Harefan Arief Faculty of Economic and Business, University of Mercubuana, Jakarta, Indonesia
Alifiah Ghaniyyu Widyaningrum Faculty of Communication Sciences, University of Mercubuana, Jakarta, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i2.1432

Keywords:

Hybrid deep learning , Context-aware recommendation systems , Privacy techniques , Data sparsity , Cold-start, Personalization

Abstract

Artificial Intelligence (AI)-based recommendation systems have become essential tools for delivering personalized services across digital platforms. However, persistent challenges related to data sparsity, cold-start conditions, dynamic user preferences, and data privacy continue to limit recommendation effectiveness. Existing studies have investigated these issues from different perspectives, yet the evidence remains fragmented across research streams focusing separately on recommendation accuracy, personalization, and privacy preservation. This study aims to provide a comprehensive synthesis of current developments in AI-based recommendation systems by examining the integration of hybrid deep learning approaches, context-aware recommendation mechanisms, and privacy-preserving techniques.

A Systematic Literature Review (SLR) was conducted following the PRISMA 2020 guidelines. An initial search of the Scopus database identified 176 records published between 2000 and 2025. After a multi-stage screening, eligibility assessment, and quality evaluation process, 68 studies were selected for detailed analysis. Descriptive, bibliometric, and thematic synthesis methods were employed to identify technological trends, implementation approaches, and emerging research directions.

The findings indicate that hybrid deep learning architectures improve recommendation performance under data sparsity and cold-start conditions, while context-aware approaches enhance personalization through dynamic adaptation to user behavior and contextual information. Privacy-preserving techniques, including differential privacy, cryptographic methods, and secure recommendation architectures, strengthen data protection without substantially reducing recommendation effectiveness. This review contributes an integrated analytical framework that links recommendation accuracy, personalization, and privacy preservation, providing guidance for the development of adaptive, trustworthy, and privacy-aware recommendation systems.

477 178

Downloads

Download data is not yet available.

References

[1] X. Feixiang, “Intelligent Personalized Recommendation Method Based on Optimized Collaborative Filtering Algorithm in Primary and Secondary Education Resource System,” IEEE Access, vol. 12, no. February, pp. 28860–28872, 2024, doi: 10.1109/ACCESS.2024.3365549. DOI: https://doi.org/10.1109/ACCESS.2024.3365549

[2] E. Kannout, M. Grodzki, and M. Grzegorowski, “Towards Addressing Item Cold-Start Problem in Collaborative Filtering by Embedding Agglomerative Clustering and FP-Growth into the Recommendation System,” Computer Science and Information Systems, vol. 20, no. 4, pp. 1343–1366, 2023, doi: 10.2298/CSIS221116052K. DOI: https://doi.org/10.2298/CSIS221116052K

[3] Y. Huang, H. Wang, and R. Wang, “Deep learning recommendation algorithm based on semantic mining,” PLoS One, vol. 17, no. 9 September, pp. 1–14, 2022, doi: 10.1371/journal.pone.0274940. DOI: https://doi.org/10.1371/journal.pone.0274940

[4] L. Li, Z. Zhang, and S. Zhang, “Hybrid Algorithm Based on Content and Collaborative Filtering in Recommendation System Optimization and Simulation,” Sci Program, vol. 2021, 2021, doi: 10.1155/2021/7427409. DOI: https://doi.org/10.1155/2021/7427409

[5] X. Wei, S. Sun, D. Wu, and L. Zhou, “Personalized Online Learning Resource Recommendation Based on Artificial Intelligence and Educational Psychology,” Front Psychol, vol. 12, no. December, pp. 1–15, 2021, doi: 10.3389/fpsyg.2021.767837. DOI: https://doi.org/10.3389/fpsyg.2021.767837

[6] L. Wu, “Collaborative Filtering Recommendation Algorithm for MOOC Resources Based on Deep Learning,” Complexity, vol. 2021, 2021, doi: 10.1155/2021/5555226. DOI: https://doi.org/10.1155/2021/5555226

[7] K. Cheng, X. Guo, X. Cui, and F. Shan, “Dynamical Modeling, Analysis, and Control of Information Diffusion over Social Networks: A Deep Learning-Based Recommendation Algorithm in Social Network,” Discrete Dyn Nat Soc, vol. 2020, 2020, doi: 10.1155/2020/3273451. DOI: https://doi.org/10.1155/2020/3273451

[8] T. Xiao and H. Shen, “Neural variational matrix factorization for collaborative filtering in recommendation systems,” Applied Intelligence, vol. 49, no. 10, pp. 3558–3569, 2019, doi: 10.1007/s10489-019-01469-6. DOI: https://doi.org/10.1007/s10489-019-01469-6

[9] L. Xu, C. Jiang, Y. Chen, Y. Ren, and K. J. Ray Liu, “User participation in collaborative filtering-based recommendation systems: A game theoretic approach,” IEEE Trans Cybern, vol. 49, no. 4, pp. 1339–1352, 2019, doi: 10.1109/TCYB.2018.2800731. DOI: https://doi.org/10.1109/TCYB.2018.2800731

[10] L. Ziegfeld, D. Di Scala, and A. H. M. Cremers, “The effect of preference elicitation methods on the user experience in conversational recommender systems,” Comput Speech Lang, vol. 89, no. April 2024, p. 101696, 2025, doi: 10.1016/j.csl.2024.101696. DOI: https://doi.org/10.1016/j.csl.2024.101696

[11] Y. Zhang, X. Lu, Y. Zhao, and Z. Yang, “PerNN: A Deep Learning-Based Recommendation Algorithm for Personalized Customization,” Electronics (Switzerland), vol. 14, no. 12, pp. 1–17, 2025, doi: 10.3390/electronics14122451. DOI: https://doi.org/10.3390/electronics14122451

[12] X. Wang, Z. Sun, H. Xue, and R. An, “Artificial Intelligence Applications to Personalized Dietary Recommendations: A Systematic Review,” Healthcare (Switzerland), vol. 13, no. 12, pp. 1–25, 2025, doi: 10.3390/healthcare13121417. DOI: https://doi.org/10.3390/healthcare13121417

[13] X. Meng, “Cross-domain information fusion and personalized recommendation in artificial intelligence recommendation system based on mathematical matrix decomposition,” Sci Rep, vol. 14, no. 1, pp. 1–13, 2024, doi: 10.1038/s41598-024-57240-6. DOI: https://doi.org/10.1038/s41598-024-57240-6

[14] D. Hou, “Personalized Book Recommendation Algorithm for University Library Based on Deep Learning Models,” J Sens, vol. 2022, 2022, doi: 10.1155/2022/3087623. DOI: https://doi.org/10.1155/2022/3087623

[15] W. Li, “Intelligent Recommendation System Based on the Infusion Algorithms with Deep Learning, Attention Network and Clustering,” International Journal of Computational Intelligence Systems, vol. 16, no. 1, pp. 1–11, 2023, doi: 10.1007/s44196-023-00264-z. DOI: https://doi.org/10.1007/s44196-023-00264-z

[16] C. Li, “An Advertising Recommendation Algorithm Based on Deep Learning Fusion Model,” J Sens, vol. 2022, 2022, doi: 10.1155/2022/1632735. DOI: https://doi.org/10.1155/2022/1632735

[17] A. da S. Dias and L. K. Wives, “Recommender system for learning objects based in the fusion of social signals, interests, and preferences of learner users in ubiquitous e-learning systems,” Pers Ubiquitous Comput, vol. 23, no. 2, pp. 249–268, 2019, doi: 10.1007/s00779-018-01197-7. DOI: https://doi.org/10.1007/s00779-018-01197-7

[18] Y. Afoudi, M. Lazaar, and M. Al Achhab, “Hybrid recommendation system combined content-based filtering and collaborative prediction using artificial neural network,” Simul Model Pract Theory, vol. 113, no. April, p. 102375, 2021, doi: 10.1016/j.simpat.2021.102375. DOI: https://doi.org/10.1016/j.simpat.2021.102375

[19] M. Wasid, R. Ali, and S. Shahab, “Adaptive genetic algorithm for user preference discovery in multi-criteria recommender systems,” Heliyon, vol. 9, no. 7, p. e18183, 2023, doi: 10.1016/j.heliyon.2023.e18183. DOI: https://doi.org/10.1016/j.heliyon.2023.e18183

[20] W. Yang, “Personalized Intelligent Recommendation Algorithm Design for Book Services Based on Deep Learning,” Wirel Commun Mob Comput, vol. 2022, 2022, doi: 10.1155/2022/9203665. DOI: https://doi.org/10.1155/2022/9203665

[21] P. Sun, “Personalized Course Resource Recommendation Algorithm Based on Deep Learning in the Intelligent Question Answering Robot Environment,” International Journal of Information Technologies and Systems Approach, vol. 16, no. 3, pp. 1–13, 2023, doi: 10.4018/IJITSA.320188. DOI: https://doi.org/10.4018/IJITSA.320188

[22] Z. Xu, H. Lin, and M. Wu, “A Course Recommendation Algorithm for a Personalized Online Learning Platform for Students From the Perspective of Deep Learning,” International Journal of Information Technology and Web Engineering, vol. 18, no. 1, pp. 1–17, 2023, doi: 10.4018/IJITWE.333603. DOI: https://doi.org/10.4018/IJITWE.333603

[23] D. Rafailidis and A. Nanopoulos, “Modeling Users Preference Dynamics and Side Information in Recommender Systems,” IEEE Trans Syst Man Cybern Syst, vol. 46, no. 6, pp. 782–792, 2016, doi: 10.1109/TSMC.2015.2460691. DOI: https://doi.org/10.1109/TSMC.2015.2460691

[24] C. Li and X. Zuo, “Classical music recommendation algorithm on art market audience expansion under deep learning,” Journal of Intelligent Systems, vol. 33, no. 1, 2024, doi: 10.1515/jisys-2023-0351. DOI: https://doi.org/10.1515/jisys-2023-0351

[25] X. Li and Z. Wang, “Support attack detection algorithm for recommendation system based on deep learning,” EURASIP J Wirel Commun Netw, vol. 2023, no. 1, 2023, doi: 10.1186/s13638-023-02269-w. DOI: https://doi.org/10.1186/s13638-023-02269-w

[26] M. E. Foster and J. Oberlander, “User preferences can drive facial expressions: Evaluating an embodied conversational agent in a recommender dialogue system,” User Model User-adapt Interact, vol. 20, no. 4, pp. 341–381, 2010, doi: 10.1007/s11257-010-9080-6. DOI: https://doi.org/10.1007/s11257-010-9080-6

[27] W. S. Kim, S. Lim, G. W. Kim, and S. M. Choi, “Extracting Implicit User Preferences in Conversational Recommender Systems Using Large Language Models,” Mathematics, vol. 13, no. 2, 2025, doi: 10.3390/math13020221. DOI: https://doi.org/10.3390/math13020221

[28] A. Gambella et al., “Improved assessment of donor liver steatosis using Banff consensus recommendations and deep learning algorithms,” J Hepatol, vol. 80, no. 3, pp. 495–504, 2024, doi: 10.1016/j.jhep.2023.11.013. DOI: https://doi.org/10.1016/j.jhep.2023.11.013

[29] W. Liang et al., “Deep Neural Network Security Collaborative Filtering Scheme for Service Recommendation in Intelligent Cyber-Physical Systems,” IEEE Internet Things J, vol. 9, no. 22, pp. 22123–22132, 2022, doi: 10.1109/JIOT.2021.3086845. DOI: https://doi.org/10.1109/JIOT.2021.3086845

[30] S. Yang, M. Korayem, K. AlJadda, T. Grainger, and S. Natarajan, “Combining content-based and collaborative filtering for job recommendation system: A cost-sensitive Statistical Relational Learning approach,” Knowl Based Syst, vol. 136, pp. 37–45, 2017, doi: 10.1016/j.knosys.2017.08.017. DOI: https://doi.org/10.1016/j.knosys.2017.08.017

[31] C. Troussas, A. Krouska, A. Koliarakis, and C. Sgouropoulou, “Harnessing the Power of User-Centric Artificial Intelligence: Customized Recommendations and Personalization in Hybrid Recommender Systems,” Computers, vol. 12, no. 5, 2023, doi: 10.3390/computers12050109. DOI: https://doi.org/10.3390/computers12050109

[32] F. Liu and W. Guo, “Personalized Recommendation Algorithm for Interactive Medical Image Using Deep Learning,” Math Probl Eng, vol. 2022, 2022, doi: 10.1155/2022/2876481. DOI: https://doi.org/10.1155/2022/2876481

[33] Y. Zhou and L. Li, “Research on Recommendation of College Mental Health Teaching Materials Based on Improved Deep Learning Algorithm,” Wirel Commun Mob Comput, vol. 2022, 2022, doi: 10.1155/2022/5184221. DOI: https://doi.org/10.1155/2022/5184221

[34] F. Zhou, “Research on Teaching Resource Recommendation Algorithm,” J Healthc Eng, vol. 2022, 2022. DOI: https://doi.org/10.1155/2022/5776341

[35] K. N. Asha and R. Rajkumar, “DCF-MLSTM: a deep security content-based filtering scheme using multiplicative BiLSTM for movie recommendation system,” International Journal of System of Systems Engineering, vol. 13, no. 1, pp. 66–82, 2023, doi: 10.1504/IJSSE.2023.10053520. DOI: https://doi.org/10.1504/IJSSE.2023.129059

[36] S. M. Z. Kashani and J. Hamidzadeh, “Feature selection by using privacy-preserving of recommendation systems based on collaborative filtering and mutual trust in social networks,” Soft comput, vol. 24, no. 15, pp. 11425–11440, 2020, doi: 10.1007/s00500-019-04605-z. DOI: https://doi.org/10.1007/s00500-019-04605-z