{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T09:31:39Z","timestamp":1777714299908,"version":"3.51.4"},"reference-count":59,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,8,25]],"date-time":"2021-08-25T00:00:00Z","timestamp":1629849600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>In the age of digital information, where the internet and social networks, as well as personalised systems, have become an integral part of everyone\u2019s life, it is often challenging to be aware of the amount of data produced daily and, unfortunately, of the potential risks caused by the indiscriminate sharing of personal data. Recently, attention to privacy has grown thanks to the introduction of specific regulations such as the European GDPR. In some fields, including recommender systems, this has inevitably led to a decrease in the amount of usable data, and, occasionally, to significant degradation in performance mainly due to information no longer being attributable to specific individuals. In this article, we present a dynamic privacy-preserving approach for recommendations in an academic context. We aim to implement a personalised system capable of protecting personal data while at the same time allowing sensible and meaningful use of the available data. The proposed approach introduces several pseudonymisation procedures based on the design goals described by the European Union Agency for Cybersecurity in their guidelines, in order to dynamically transform entities (e.g., persons) and attributes (e.g., authored papers and research interests) in such a way that any user processing the data are not able to identify individuals. We present a case study using data from researchers of the Georg Eckert Institute for International Textbook Research (Brunswick, Germany). Building a knowledge graph and exploiting a Neo4j database for data management, we first generate several pseudoN-graphs, being graphs with different rates of pseudonymised persons. Then, we evaluate our approach by leveraging the graph embedding algorithm node2vec to produce recommendations through node relatedness. The recommendations provided by the graphs in different privacy-preserving scenarios are compared with those provided by the fully non-pseudonymised graph, considered as the baseline of our evaluation. The experimental results show that, despite the structural modifications to the knowledge graph structure due to the de-identification processes, applying the approach proposed in this article allows for preserving significant performance values in terms of precision.<\/jats:p>","DOI":"10.3390\/computers10090107","type":"journal-article","created":{"date-parts":[[2021,8,26]],"date-time":"2021-08-26T00:19:26Z","timestamp":1629937166000},"page":"107","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Dynamic Privacy-Preserving Recommendations on Academic Graph Data"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5506-3020","authenticated-orcid":false,"given":"Erasmo","family":"Purificato","sequence":"first","affiliation":[{"name":"Georg Eckert Institute for International Textbook Research Member of the Leibniz Association, Celler Stra\u00dfe 3, 38114 Brunswick, Germany"},{"name":"Faculty of Computer Science, Otto von Guericke University Magdeburg, Universit\u00e4tsplatz 2, 39104 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5290-0321","authenticated-orcid":false,"given":"Sabine","family":"Wehnert","sequence":"additional","affiliation":[{"name":"Georg Eckert Institute for International Textbook Research Member of the Leibniz Association, Celler Stra\u00dfe 3, 38114 Brunswick, Germany"},{"name":"Faculty of Computer Science, Otto von Guericke University Magdeburg, Universit\u00e4tsplatz 2, 39104 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3621-4118","authenticated-orcid":false,"given":"Ernesto William","family":"De Luca","sequence":"additional","affiliation":[{"name":"Georg Eckert Institute for International Textbook Research Member of the Leibniz Association, Celler Stra\u00dfe 3, 38114 Brunswick, Germany"},{"name":"Faculty of Computer Science, Otto von Guericke University Magdeburg, Universit\u00e4tsplatz 2, 39104 Magdeburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Pavan, M., Lee, T., and De Luca, E.W. (2015, January 21\u201322). Semantic enrichment for adaptive expert search. Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business, Graz, Austria. Number Article 36 in i-KNOW\u201915.","DOI":"10.1145\/2809563.2809621"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mangaravite, V., Santos, R.L., Ribeiro, I.S., Gon\u00e7alves, M.A., and Laender, A.H. (2016, January 17\u201321). The LExR collection for expertise retrieval in academia. Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, Pisa, Italy.","DOI":"10.1145\/2911451.2914678"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"9324","DOI":"10.1109\/ACCESS.2018.2890388","article-title":"Scientific Paper Recommendation: A Survey","volume":"7","author":"Bai","year":"2019","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hassan, H.A.M. (2017, January 9\u201310). Personalized research paper recommendation using deep learning. Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization, Bratislava, Slovakia.","DOI":"10.1145\/3079628.3079708"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.jnca.2017.12.004","article-title":"PAVE: Personalized Academic Venue recommendation Exploiting co-publication networks","volume":"104","author":"Yu","year":"2018","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/4236.968832","article-title":"Privacy Risks in Recommender Systems","volume":"5","author":"Ramakrishnan","year":"2001","journal-title":"IEEE Internet Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lam, S.K., Frankowski, D., and Riedl, J. (2006). Do You Trust Your Recommendations? An Exploration of Security and Privacy Issues in Recommender Systems. Internation Conference on Emerging Trends in Information and Communication Security, Springer.","DOI":"10.1007\/11766155_2"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Aghasian, E., Garg, S., and Montgomery, J. (2018). User\u2019s Privacy in Recommendation Systems Applying Online Social Network Data, A Survey and Taxonomy. Big Data Recommender Systems: Recent Trends and Advances, The Institution of Engineering and Technology.","DOI":"10.1049\/PBPC035F_ch12"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ramzan, N., van Zwol, R., Lee, J.S., Cl\u00fcver, K., and Hua, X.S. (2013). Privacy in Recommender Systems. Social Media Retrieval, Springer.","DOI":"10.1007\/978-1-4471-4555-4"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.eng.2018.02.005","article-title":"Toward Privacy-Preserving Personalized Recommendation Services","volume":"4","author":"Wang","year":"2018","journal-title":"Engineering"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Catherine, R., and Cohen, W. (2016, January 15\u201319). Personalized Recommendations using Knowledge Graphs: A Probabilistic Logic Programming Approach. Proceedings of the 10th ACM Conference on Recommender Systems, RecSys \u201916, Boston, MA, USA.","DOI":"10.1145\/2959100.2959131"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Palumbo, E., Rizzo, G., and Troncy, R. (2017, January 27\u201331). entity2rec: Learning User-Item Relatedness from Knowledge Graphs for Top-N Item Recommendation. Proceedings of the Eleventh ACM Conference on Recommender Systems, RecSys \u201917, Como, Italy.","DOI":"10.1145\/3109859.3109889"},{"key":"ref_13","unstructured":"European Union Agency for Cybersecurity (ENISA) (2019). Pseudonymisation Techniques and Best Practices\u2014Recommendations on Shaping Technology According to Data Protection and Privacy Provisions, ENISA. Technical Report."},{"key":"ref_14","unstructured":"Data Protection Focus Group (2018). Requirements for the Use of Pseudonymisation Solutions in Compliance with Data Protection Regulations, German Society for Data Protection and Data Security. Technical Report."},{"key":"ref_15","first-page":"855","article-title":"node2vec: Scalable Feature Learning for Networks","volume":"2016","author":"Grover","year":"2016","journal-title":"KDD"},{"key":"ref_16","unstructured":"Wang, J., Arriaga, A., Tang, Q., and Ryan, P.Y.A. (2018). CryptoRec: Privacy-preserving Recommendation as a Service. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3212509","article-title":"Efficient Privacy-Preserving Matrix Factorization for Recommendation via Fully Homomorphic Encryption","volume":"21","author":"Kim","year":"2018","journal-title":"Acm Trans. Priv. Secur. (TOPS)"},{"key":"ref_18","unstructured":"Gentry, C. (June, January 31). Fully homomorphic encryption using ideal lattices. Proceedings of the Forty-First Annual ACM Symposium on Theory of Computing, STOC \u201909, Bethesda, MD, USA."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/s10207-007-0049-3","article-title":"Alambic: A privacy-preserving recommender system for electronic commerce","volume":"7","author":"Brassard","year":"2008","journal-title":"Int. J. Inf. Secur."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Nikolaenko, V., Ioannidis, S., Weinsberg, U., Joye, M., Taft, N., and Boneh, D. (2013, January 4\u20138). Privacy-preserving matrix factorization. Proceedings of the 2013 ACM SIGSAC Conference on Computer & Communications Security, CCS \u201913, Berlin, Germany.","DOI":"10.1145\/2508859.2516751"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s41019-016-0020-2","article-title":"A Practical Privacy-Preserving Recommender System","volume":"1","author":"Badsha","year":"2016","journal-title":"Data Sci. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"van Tilborg, H.C.A., and Jajodia, S. (2011). ElGamal Public Key Encryption. Encyclopedia of Cryptography and Security, Springer.","DOI":"10.1007\/978-1-4419-5906-5"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y.X., and Smola, A. (2015, January 16\u201320). Fast Differentially Private Matrix Factorization. Proceedings of the 9th ACM Conference on Recommender Systems, RecSys \u201915, Vienna, Austria.","DOI":"10.1145\/2792838.2800191"},{"key":"ref_24","unstructured":"McSherry, F., and Mironov, I. (July, January 28). Differentially private recommender systems: Building privacy into the Netflix Prize contenders. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201909, Paris, France."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Berlioz, A., Friedman, A., Kaafar, M.A., Boreli, R., and Berkovsky, S. (2015, January 16\u201320). Applying Differential Privacy to Matrix Factorization. Proceedings of the 9th ACM Conference on Recommender Systems, RecSys \u201915, Vienna, Austria.","DOI":"10.1145\/2792838.2800173"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhu, J., He, P., Zheng, Z., and Lyu, M.R. (July, January 27). A Privacy-Preserving QoS Prediction Framework for Web Service Recommendation. Proceedings of the 2015 IEEE International Conference on Web Services, New York, NY, USA.","DOI":"10.1109\/ICWS.2015.41"},{"key":"ref_27","unstructured":"European Union Agency for Cybersecurity (ENISA) (2018). Recommendations on Shaping Technology According to GDPR Provisions\u2014An Overview on Data Pseudonymisation, ENISA. Technical Report."},{"key":"ref_28","unstructured":"Pfitzmann, A., and Hansen, M. (2021, August 18). A Terminology for Talking about Privacy by Data Minimization: Anonymity, Unlinkability, Undetectability, Unobservability, Pseudonymity, and Identity Management. Technical Report; Dresden, Germany. Available online: https:\/\/dud.inf.tu-dresden.de\/literatur\/Anon_Terminology_v0.34.pdf."},{"key":"ref_29","first-page":"284","article-title":"Anonymous Data v. Personal Data\u2014A False Debate: An EU Perspective on Anonymization, Pseudonymization and Personal Data","volume":"34","author":"Knight","year":"2017","journal-title":"Wis. Int. Law J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"289","DOI":"10.2478\/popets-2019-0048","article-title":"ScrambleDB: Oblivious (Chameleon) Pseudonymization-as-a-Service","volume":"2019","author":"Lehmann","year":"2019","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Friedrich, M., K\u00f6hn, A., Wiedemann, G., and Biemann, C. (2019, January 28). Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.","DOI":"10.18653\/v1\/P19-1584"},{"key":"ref_32","first-page":"101","article-title":"Deep Learning Approaches Outperform Conventional Strategies in De-Identification of German Medical Reports","volume":"267","author":"Amr","year":"2019","journal-title":"Stud. Health Technol. Inform."},{"key":"ref_33","unstructured":"Eder, E., Krieg-Holz, U., and Hahn, U. (2020, January 11\u201316). CodE Alltag 2.0\u2014A Pseudonymized German-Language Email Corpus. Proceedings of the 12th Language Resources and Evaluation Conference, Marseille, France."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.procs.2019.04.043","article-title":"GDPR principles in Data protection encourage pseudonymization through most popular and full-personalized devices - mobile phones","volume":"151","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_35","first-page":"27","article-title":"On privacy-preserving context-aware recommender system","volume":"8","author":"Yao","year":"2015","journal-title":"Int. J. Hybrid Inf. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s10462-012-9359-6","article-title":"A study of the dynamic features of recommender systems","volume":"43","author":"Rana","year":"2015","journal-title":"Artif. Intell. Rev."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1504\/IJWET.2018.095184","article-title":"A review on the dynamics of social recommender systems","volume":"13","author":"Rana","year":"2018","journal-title":"Int. J. Web Eng. Technol."},{"key":"ref_38","unstructured":"Koren, Y. (July, January 28). Collaborative filtering with temporal dynamics. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201909, Paris, France."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Jannach, D., and Ludewig, M. (2017, January 27\u201331). When Recurrent Neural Networks meet the Neighborhood for Session-Based Recommendation. Proceedings of the 11th ACM Conference on Recommender Systems, RecSys \u201917, Como, Italy.","DOI":"10.1145\/3109859.3109872"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Quadrana, M., Karatzoglou, A., Hidasi, B., and Cremonesi, P. (2017, January 27\u201331). Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks. Proceedings of the Eleventh ACM Conference on Recommender Systems, RecSys \u201917, New York, NY, USA.","DOI":"10.1145\/3109859.3109896"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"You, J., Wang, Y., Pal, A., Eksombatchai, P., Rosenberg, C., and Leskovec, J. (2019, January 13\u201317). Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems. Proceedings of the The World Wide Web Conference 2019, San Francisco, CA, USA.","DOI":"10.1145\/3308558.3313747"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ricci, F., Rokach, L., Shapira, B., and Kantor, P.B. (2011). Context-Aware Recommender Systems. Recommender Systems Handbook, Springer.","DOI":"10.1007\/978-0-387-85820-3"},{"key":"ref_43","unstructured":"Varatharajah, Y., Chen, H., Trotter, A., and Iyer, R. (2020, January 26). A dynamic human-in-the-loop recommender system for evidence-based clinical staging of COVID-19. Proceedings of the 5th International Workshop on Health Recommender Systems, Rio de Janeiro, Brazil."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Erkin, Z., Veugen, T., and Lagendijk, R.L. (2013, January 18\u201321). Privacy-preserving recommender systems in dynamic environments. Proceedings of the 2013 IEEE International Workshop on Information Forensics and Security (WIFS), Guangzhou, China.","DOI":"10.1109\/WIFS.2013.6707795"},{"key":"ref_45","unstructured":"Zhu, T., Li, J., Hu, X., Xiong, P., and Zhou, W. (2020). The Dynamic Privacy-preserving Mechanisms for Online Dynamic Social Networks. IEEE Trans. Knowl. Data Eng."},{"key":"ref_46","unstructured":"United States Government Accountability Office (GAO) (2008). Privacy: Alternatives Exist for Enhancing Protection of Personally Identifiable Information (GAO-08-536), United States Government Accountability Office (GAO). Technical Report."},{"key":"ref_47","unstructured":"Garfinkel, S.L. (2015). De-Identification of Personal Information, National Institute of Standards and Technology Internal Report 8053. Technical Report."},{"key":"ref_48","unstructured":"Almeida, F., and Xex\u00e9o, G. (2019). Word embeddings: A survey. arXiv."},{"key":"ref_49","unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv."},{"key":"ref_50","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"012116","DOI":"10.1088\/1742-6596\/978\/1\/012116","article-title":"A comparative study of Message Digest 5(MD5) and SHA256 algorithm","volume":"978","author":"Rachmawati","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: A lexical database for English","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"key":"ref_53","unstructured":"Honnibal, M., Montani, I., Van Landeghem, S., and Boyd, A. (2021, August 18). spaCy: Industrial-strength Natural Language Processing in Python. Web documentation. Available online: https:\/\/spacy.io\/."},{"key":"ref_54","unstructured":"Kusner, M., Sun, Y., Kolkin, N., and Weinberger, K. (2015, January 6\u201311). From word embeddings to document distances. Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France."},{"key":"ref_55","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., and Artzi, Y. (2019). Bertscore: Evaluating text generation with bert. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., and Cohan, A. (2019). SciBERT: A pretrained language model for scientific text. arXiv.","DOI":"10.18653\/v1\/D19-1371"},{"key":"ref_57","unstructured":"European Union Agency for Cybersecurity (ENISA) (2014). Privacy and Data Protection by Design\u2014From Policy to Engineering, ENISA. Technical Report."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Palumbo, E., Rizzo, G., Troncy, R., Baralis, E., Osella, M., and Ferro, E. (2018, January 3\u20137). Knowledge graph embeddings with node2vec for item recommendation. Proceedings of the 15th European Semantic Web Conference, Heraklion, Greece.","DOI":"10.1007\/978-3-319-98192-5_22"},{"key":"ref_59","unstructured":"Pavan, M., and De Luca, E.W. (2015, January 18). Semantic-based expert search in textbook research archives. Proceedings of the 5th International Workshop on Semantic Digital Archives, Poznan, Poland."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/10\/9\/107\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:51:59Z","timestamp":1760165519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/10\/9\/107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,25]]},"references-count":59,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["computers10090107"],"URL":"https:\/\/doi.org\/10.3390\/computers10090107","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,25]]}}}