DNGR: Deep Neural Graph-Based Recommendation System for Scholarly Paper Retrieval

  • Authors

    • Dr. M Sathya Associate Professor, Department of Computer Science and Engineering, Nadar Saraswathi ‎College of Engineering and Technology, Theni
    • Arulmurugan Ramu Associate Professor, Department of Computational Sciences and Software Engineering, ‎Heriot-Watt International faculty, K, Zhubanov Aktobe regional University, Kazakhstan
    • Velkumar K Assistant Professor, Department of Computer Science and Engineering, Nadar Saraswathi ‎College of Engineering and Technology, Theni
    • M Bhavani Assistant Professor, Department of Information Technology, Nadar Saraswathi ‎College of Engineering and Technology, Theni
    https://doi.org/10.14419/dzzstd42

    Received date: July 16, 2025

    Accepted date: August 20, 2025

    Published date: September 9, 2025

  • Citation Recommendation; Graph Neural Networks (GNNs); Deep Learning; SciBERT; ‎Heterogeneous Graphs; Academic Knowledge Graph; Scholarly Retrieval‎.

  • Abstract

    With the exponential growth of scholarly publications, identifying relevant literature has ‎become increasingly challenging for researchers. Traditional recommendation methods—such ‎as collaborative filtering, content-based filtering, and citation analysis—often struggle to scale ‎or capture deep semantic and structural relationships. In this study, we introduce DNGR ‎‎(Deep Neural Graph-based Recommendation), a novel model that combines graph neural ‎networks (GNNs) with SciBERT-based semantic embeddings to enhance scholarly paper ‎recommendations. DNGR constructs a heterogeneous academic knowledge graph ‎incorporating citation links, author collaborations, and topical associations. Each paper is ‎represented by both its contextual semantics and structural position in the academic network. ‎We evaluate DNGR on the AMiner v12 DBLP-Citation Network, comprising over 4.8 million ‎papers and 45 million citation edges. Experiments using standard information retrieval ‎metrics—Mean Average Precision (MAP), Mean Reciprocal Rank (MRR), and Normalized ‎Discounted Cumulative Gain (NDCG)—demonstrate that DNGR outperforms state-of-the-art-‎art baselines, achieving up to a 92% improvement in recommendation accuracy over methods ‎like MSCN and Google Scholar. Our results highlight the potential of integrating deep ‎contextual and graph-based signals for scalable and accurate citation recommendation. We ‎also discuss limitations, ethical considerations, and potential extensions to multi-disciplinary ‎datasets‎.

  • References

    1. Liang, Y. & Lee, L. (2023). A Systematic Review of Citation Recommendation Over the Past Two Decades. International Journal on Semantic Web and Information Systems (IJSWIS), 19(1), 1-22. https://doi.org/10.4018/IJSWIS.324071.
    2. Haruna, K., Ismail, M. A., Bichi, A. B., Chang, V., Wibawa, S., & Herawan, T. (2018). A citation-based recommender system for scholarly paper recommendation. In Computational Science and Its Applications – ICCSA 2018 (pp. 514-525). (Lecture Notes in Computer Sci-ence). https://doi.org/10.1007/978-3-319-95162-1_35.
    3. Kanwal, T., & Amjad, T. (2024). Research paper recommendation system based on multiple features from the citation network. Scientometrics, 129(9), 5493–5531. https://doi.org/10.1007/s11192-024-05109-w.
    4. Bala Subramanian C., K. V. (2023). Deep Learning-Assisted Citation Recommendation System Using Multi- cell RNN Approach. Tuijin Jishu/Journal of Propulsion Technology, 44(2). https://doi.org/10.52783/tjjpt.v44.i2.135.
    5. Gündoğan, E., Kaya, M., & Daud, A. (2023). Deep learning for journal recommendation system of research papers. Scientometrics, 128(1), 461–481. https://doi.org/10.1007/s11192-022-04535-y.
    6. Li, W. (2024). Scientific paper recommender system using deep learning and link prediction in citation network. Heliyon, 10(14), e34685. https://doi.org/10.1016/j.heliyon.2024.e34685.
    7. Abbasi, I. I., Abbas, M. A., Hammad, S., Jilani, M. T., Ahmed, S., & un Nisa, S. (2020). A hybrid approach for the recommendation of scholarly journals. In 2020 International Conference on Information Science and Communication Technology (ICISCT) (pp. 1–6). IEEE. https://doi.org/10.1109/ICISCT49550.2020.9080032.
    8. Ali, Z., Qi, G., Muhammad, K., Ali, B., & Abro, W. A. (2020a). Paper recommendation based on heterogeneous network embedding. Knowledge-Based Systems, 210, 106438. https://doi.org/10.1016/j.knosys.2020.106438.
    9. Ali, Z., Kefalas, P., Muhammad, K., Ali, B., & Imran, M. (2020b). Deep learning in citation recommendation models survey. Expert Systems with Applications, 162, 113790. https://doi.org/10.1016/j.eswa.2020.113790.
    10. Ali, Z., Qi, G., Muhammad, K., Kefalas, P., & Khusro, S. (2021). Global citation recommendation employing generative adversarial network. Ex-pert Systems with Applications, 180, 114888. https://doi.org/10.1016/j.eswa.2021.114888.
    11. Ali, Z., Qi, G., Kefalas, P., Khusro, S., Khan, I., & Muhammad, K. (2022). SPR-SMN: Scientific paper recommendation employing SPECTER with memory network. Scientometrics, 127, 6763–6785. https://doi.org/10.1007/s11192-022-04425-3.
    12. Beltagy, I., Lo, K., & Cohan, A. (2019). SciBERT: A pretrained language model for scientific text. arXiv. https://doi.org/10.18653/v1/D19-1371.
    13. Bobadilla, J., Ortega, F., Hernando, A., & Gutiérrez, A. (2013). Recommender systems survey. Knowledge-Based Systems, 46, 109–132. https://doi.org/10.1016/j.knosys.2013.03.012.
    14. Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017). Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5, 135–146. https://doi.org/10.1162/tacl_a_00051.
    15. Bhagavatula, C., Feldman, S., Power, R., & Ammar, W. (2018). Content-based citation recommendation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Vol. 1: Long Papers, pp. 238–251). Association for Computational Linguistics. https://doi.org/10.18653/v1/N18-1022.
    16. Liu, H., Kong, X., Bai, X., Wang, W., Bekele, T. M., & Xia, F. (2015). Context-based collaborative filtering for citation recommendation. IEEE Access, 3, 1695–1703. https://doi.org/10.1109/ACCESS.2015.2481320.
    17. Al-Hassan, M., Abu-Salih, B., Alshdaifat, E. A., Aloqaily, A., & Rodan, A. (2024). An improved fusion-based semantic similarity measure for ef-fective collaborative filtering recommendations. International Journal of Computational Intelligence Systems, 17(1), 45. https://doi.org/10.1007/s44196-024-00429-4.
    18. Nair, A. M., Benny, O., & George, J. (2021). Content-based scientific article recommendation system using deep learning technique. In V. Suma, J. I. Z. Chen, Z. Baig, & H. Wang (Eds.), Inventive Systems and Control (Lecture Notes in Networks and Systems, Vol. 204, pp. 965–977). Springer, Singapore. https://doi.org/10.1007/978-981-16-1395-1_70.
    19. Gonzalez Camacho, L. A., & Alves-Souza, S. N. (2018). Social network data to alleviate cold-start in recommender system: A systematic review. Information Processing & Management, 54(4), 529–544. https://doi.org/10.1016/j.ipm.2018.03.004.

  • Downloads

  • How to Cite

    Sathya , D. M. ., Ramu, A., K, V. ., & Bhavani, M. . (2025). DNGR: Deep Neural Graph-Based Recommendation System for Scholarly Paper Retrieval. International Journal of Basic and Applied Sciences, 14(5), 300-305. https://doi.org/10.14419/dzzstd42