A Personalized and Explainable News Recommendation Framework Leveraging User Clickstreams and Content Semantics
Kalyan Chakravarthy N S
Center for Quantum Computing, QIS College of Engineering and Technology, Ongole, Andhra Pradesh, India, Institute of Computer Science and Digital Innovation, UCSI University, 1, Jalan UCSI, UCSI Heights (Taman Connaught), Cheras, Kuala Lumpur, Malaysia.
Department of Internet of Things, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India, Institute of Computer Science and Digital Innovation, UCSI University, 1, Jalan UCSI, UCSI Heights (Taman Connaught), Cheras, Kuala Lumpur, Malaysia.
MindReader introduces an interpretable and personalized news recommender system that integrates clickstream data to summarize transformer-based content semantics and provide token-level biased attribution. Unlike classical recommender systems, which often operate as black boxes, MindReader offers actionable interpretability by utilizing Shapley Additive explanations (SHAP) to reveal the word-level contributions behind each recommendation decision. This model combines both user reading history and article content extraction through a unified framework, incorporating temporal patterns and semantic embeddings. MindReader demonstrates state-of-the-art AUC and coherence scores on real-world news datasets, outperforming several strong baselines, including TF-IDF and neural content models. Human evaluation confirms its superiority. SHAP-based overlays closely align with user attention patterns, while error case analysis highlights resilience against linguistic noise and clickbait content. A key differentiator of MindReader lies in its commitment to not only achieving high performance but also ensuring transparency and trust qualities vital for the deployment of AI in sensitive areas such as journalism, education, and civic communication. This transparency allows users to not only see what content is recommended but also understand the reasoning behind it. In alignment with the UN Sustainable Development Goals (SDG 4 – Quality Education, SDG 9 – Innovation and Infrastructure, and SDG 16 – Strong Institutions), MindReader advocates for an interpretable AI framework for public information dissemination. The architecture proposed in this work offers a scalable, user-centric, and SDG-compliant approach to the implementation of explainable recommended systems.
Keywords
Explainable Recommender Systems, Transformer Models for Recommendation, SHAP Interpretability, User Clickstream Modeling, News Personalization, Responsible AI for Information Systems.
A. A. ABRO, M. S. H. TALPUR, and A. K. JUMANİ, “Natural Language Processing Challenges and Issues: A Literature Review,” Gazi University Journal of Science, vol. 36, no. 4, pp. 1522–1536, Dec. 2023, doi: 10.35378/gujs.1032517.
A. Alslaity and T. Tran, “Users’ Responsiveness to Persuasive Techniques in Recommender Systems,” Frontiers in Artificial Intelligence, vol. 4, Jul. 2021, doi: 10.3389/frai.2021.679459.
G. Van den Broeck, A. Lykov, M. Schleich, and D. Suciu, “On the Tractability of SHAP Explanations,” Journal of Artificial Intelligence Research, vol. 74, pp. 851–886, Jun. 2022, doi: 10.1613/jair.1.13283.
Devlin, J., Chang, M., Lee, K. and Toutanova, K. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv (Cornell University). (Jan. 2018). DOI:https://doi.org/10.48550/arXiv.1810.04805.
Fan, W., Zhao, Z., Li, J., Liu, Y., Mei, X., Wang, Y., Tang, J. and Li, Q. 2023. Recommender Systems in the Era of Large Language Models (LLMs). arXiv (Cornell University). (Jan. 2023). DOI:https://doi.org/10.48550/arXiv.2307.02046.
J. De Freitas, S. Agarwal, B. Schmitt, and N. Haslam, “Psychological factors underlying attitudes toward AI tools,” Nature Human Behaviour, vol. 7, no. 11, pp. 1845–1854, Nov. 2023, doi: 10.1038/s41562-023-01734-2.
S. Guo, Y. Wang, H. Yuan, Z. Huang, J. Chen, and X. Wang, “TAERT: Triple-Attentional Explainable Recommendation with Temporal Convolutional Network,” Information Sciences, vol. 567, pp. 185–200, Aug. 2021, doi: 10.1016/j.ins.2021.03.034.
Jain, S. and Wallace, B. 2019. Attention is not Explanation. arXiv (Cornell University). (Jan. 2019). DOI:https://doi.org/10.48550/arxiv.1902.10186.
D. Jang, S.-K. Lee, and Q. Li, “ITS-Rec: A Sequential Recommendation Model Using Item Textual Information,” Electronics, vol. 14, no. 9, p. 1748, Apr. 2025, doi: 10.3390/electronics14091748.
Q. Jia, J. Li, Q. Zhang, X. He, and J. Zhu, “RMBERT: News Recommendation via Recurrent Reasoning Memory Network over BERT,” Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1773–1777, Jul. 2021, doi: 10.1145/3404835.3463234.
Jiang, H., Li, C. and An, M. 2024. Time Matters: Enhancing Pre-trained News Recommendation Models with Robust User Dwell Time Injection. arXiv (Cornell University). (May 2024). DOI:https://doi.org/10.48550/arxiv.2405.12486.
J. Leonhardt, K. Rudra, and A. Anand, “Extractive Explanations for Interpretable Text Ranking,” ACM Transactions on Information Systems, vol. 41, no. 4, pp. 1–31, Mar. 2023, doi: 10.1145/3576924.
E. Lex, D. Kowald, P. Seitlinger, T. N. T. Tran, A. Felfernig, and M. Schedl, “Psychology-informed Recommender Systems,” Foundations and Trends® in Information Retrieval, vol. 15, no. 2, pp. 134–242, 2021, doi: 10.1561/1500000090.
L. Li, Y. Zhang, and L. Chen, “On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance,” ACM Transactions on Intelligent Systems and Technology, vol. 14, no. 2, pp. 1–24, Feb. 2023, doi: 10.1145/3569423.
Li, W., Xu, Y., Li, Y. and Huang, Y. 2025. Display Content, Display Methods and Evaluation Methods of the HCI in Explainable Recommender Systems: A Survey. (2025). DOI:https://doi.org/10.48550/ARXIV.2505.09065.
W. Liu, B. Liu, J. Qin, X. Zhang, W. Huang, and Y. Wang, “Fairness identification of large language models in recommendation,” Scientific Reports, vol. 15, no. 1, Feb. 2025, doi: 10.1038/s41598-025-89965-3.
Ma, Q., Ren, X. and Huang, C. 2024. XRec: Large Language Models for Explainable Recommendation. arXiv (Cornell University). (Jun. 2024). DOI:https://doi.org/10.48550/arxiv.2406.02377.
G. de Souza Pereira Moreira, F. Ferreira, and A. M. da Cunha, “News Session-Based Recommendations using Deep Neural Networks,” Proceedings of the 3rd Workshop on Deep Learning for Recommender Systems, pp. 15–23, Oct. 2018, doi: 10.1145/3270323.3270328.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Conceptualization: Kalyan Chakravarthy N S, Muthuramya C, Soujanya M, Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy;
Methodology: Kalyan Chakravarthy N S, Muthuramya C and Soujanya M;
Software: Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy;
Data Curation: Kalyan Chakravarthy N S, Muthuramya C and Soujanya M;
Writing- Original Draft Preparation: Kalyan Chakravarthy N S, Muthuramya C, Soujanya M, Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy;
Visualization: Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy;
Investigation: Kalyan Chakravarthy N S, Muthuramya C and Soujanya M;
Supervision: Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy;
Validation: Kalyan Chakravarthy N S, Muthuramya C and Soujanya M;
Writing- Reviewing and Editing: Kalyan Chakravarthy N S, Muthuramya C, Soujanya M, Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy;
All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
The authors would like to thank to the reviewers for nice comments on the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Jafar Ali Ibrahim Syed Masood
Department of Internet of Things, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India, Institute of Computer Science and Digital Innovation, UCSI University, 1, Jalan UCSI, UCSI Heights (Taman Connaught), Cheras, Kuala Lumpur, Malaysia.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Kalyan Chakravarthy N S, Muthuramya C, Soujanya M, Jafar Ali Ibrahim Syed Masood and Raenu Kolandaisamy, “A Personalized and Explainable News Recommendation Framework Leveraging User Clickstreams and Content Semantics”, Journal of Machine and Computing, vol.5, no.4, pp. 2756-2771, October 2025, doi: 10.53759/7669/jmc202505210.
