SavedAdd your journal

Journals / International Journal of Multidisciplinary Studies and Innovative Technologies / 2026 / Cilt: 10 Sayı: 1

A Graph-Based Article Recommendation System with Multilayer Citation

Çok Katmanlı Atıf Yapısına Sahip Graf Tabanlı Bir Makale Öneri Sistemi

Umut Karadurmuş(EGE ÜNİVERSİTESİ, FEN BİLİMLERİ ENSTİTÜSÜ, BİLGİSAYAR MÜHENDİSLİĞİ (YL) (TEZLİ))0009-0009-2231-6376
Züleyha Akusta Dağdeviren(EGE UNIVERSITY, FACULTY OF ENGINEERING, DEPARTMENT OF COMPUTER ENGINEERING)0000-0001-9365-326X
Pages
64–71
Publication Date
2026-08-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Across 358 held-out direct citations, 45.5% re-entered the two-hop candidate pool; Recall@10 was 0.112 overall and 0.245 when conditioned on candidate coverage.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:We present a citation-centered article recommendation system that ranks works in a heterogeneous two-hop OpenAlex graph by combining structural connectivity with concept overlap and venue signals.
📊
Key Findings & Data:Ten target articles were evaluated from a data snapshot collected on March 8, 2026.
💡
Conclusion & Impact:Across 358 held-out direct citations, 45.5% re-entered the two-hop candidate pool; Recall@10 was 0.112 overall and 0.245 when conditioned on candidate coverage.
🔬Design:Lab & Field Experiment
📍Scope:2026 Verileri
⚙️Variables:atıf ağları · karmaşık ağlar · öneri sistemleri

Abstract

We present a citation-centered article recommendation system that ranks works in a heterogeneous two-hop OpenAlex graph by combining structural connectivity with concept overlap and venue signals. Direct references form a primary, local-reading tier, whereas references reached through them form a secondary discovery tier. Ten target articles were evaluated from a data snapshot collected on March 8, 2026. Because concept-set Jaccard is also a scoring input, we supplemented it with an independent abstract-level TF–IDF cosine analysis and a leave-one-out hidden-reference experiment. For the full model, mean abstract cosine was 0.045 for primary and 0.029 for secondary recommendations among available abstract pairs. Across 358 held-out direct citations, 45.5% re-entered the two-hop candidate pool; Recall@10 was 0.112 overall and 0.245 when conditioned on candidate coverage. The networks were sparse and weakly connected when citation direction was ignored, although these properties are partly induced by ego-network construction. The findings show that a lightweight and interpretable hybrid can recover relevant citation-neighborhood works without model training, while also exposing candidate-generation and ground-truth limitations that require larger labelled or user-based evaluation.

Özet

Bu çalışmada, kullanıcı tarafından belirtilen bir hedef makale için ilgili çalışmaları belirlemek amacıyla akademik atıf ağlarının yapısından yararlanan atıf merkezli bir makale öneri sistemi sunuyoruz. OpenAlex kullanılarak, hedef makaleyi, birincil ve ikincil atıflarını, konu kavramlarını ve yayın mecralarını içeren heterojen çok katmanlı bir çizge oluşturuyoruz. Aday makaleler, yerel alaka için birincil öneriler ile daha geniş keşif için ikincil öneriler arasında bilinçli bir ayrımı korurken, yapısal bağlantılılığı anlamsal benzerlik ve yayın mecrası tabanlı tamamlayıcı sinyallerle bütünleştiren verimli bir hibrit puanlama modeli ile sıralanmaktadır. Sistem, kesin doğruluk niteliğinde alaka etiketleri mevcut olmadığı için vekil metrikler (Jaccard benzerliği ve ablasyon kararlılığı) kullanılarak atıf öneri literatüründen seçilen on hedef makale üzerinde değerlendirilmiştir. Oluşturulan ağlar büyük, seyrek ve iyi bağlantılıdır ve öneriler, birincil öneriler için 0.210 ve ikincil öneriler için 0.187 ortalama Jaccard benzerliği skorlarıyla tutarlı konu uyumu göstermiştir. Bu bulgular, basit ve yorumlanebilir bir hibrit tasarımın, pahalı gömme modelleri veya kullanıcı etkileşim verileri gerektirmeden hem yapısal olarak temellendirilmiş hem de anlamsal olarak anlamlı öneriler üretebileceğini göstermektedir.

🔖

Cite This Article

Karadurmuş, U., Dağdeviren, Z. A. (2026). A Graph-Based Article Recommendation System with Multilayer Citation. International Journal of Multidisciplinary Studies and Innovative Technologies, Cilt: 10 Sayı: 1, 64–71. https://doi.org/10.36287/ijmsit.10.1.7

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (20)

  1. J. Priem, H. Piwowar, and R. Orr, “OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts,” arXiv preprint arXiv:2205.01833, 2022.
  2. L. Lü and T. Zhou, “Link prediction in complex networks: A survey,” Physica A: Statistical Mechanics and its Applications, vol. 390, no. 6, pp. 1150–1170, 2011.
  3. Y. Liang and L.-K. Lee, “A Systematic Review of Citation Recommendation Over the Past Two Decades,” International Journal on Semantic Web and Information Systems, vol. 19, no. 1, 2023.
  4. J. Son and S. B. Kim, “Academic paper recommender system using multilevel citation networks,” Decision Support Systems, vol. 105, pp. 24–33, 2018.
  5. J. Zhang, H. Wu, Y. Lu, and X. Wang, “Citation recommendation using semantic representation of cited papers’ relations and content,” Expert Systems with Applications, vol. 198, 2022, Art. no. 115826.
  6. C. Pornprasit, X. Liu, and S. Tuarob, “Enhancing citation recommendation using citation network embedding,” Scientometrics, vol. 127, pp. 233–264, 2022.
  7. M. Färber and A. Sampath, “HybridCite: A Hybrid Model for Context-Aware Citation Recommendation,” in Proc. ACM/IEEE Joint Conf. on Digital Libraries (JCDL), 2020.
  8. D. J. Watts and S. H. Strogatz, “Collective dynamics of ‘small-world’ networks,” Nature, vol. 393, no. 6684, pp. 440–442, 1998.
  9. A.-L. Barabási and R. Albert, “Emergence of scaling in random networks,” Science, vol. 286, no. 5439, pp. 509–512, 1999.
  10. D. B. West, Introduction to Graph Theory, 2nd ed. Upper Saddle River, NJ, USA: Prentice Hall, 2001.
  11. N. J. van Eck and L. Waltman, “CitNetExplorer: A new software tool for analyzing and visualizing citation networks,” Journal of Informetrics, vol. 8, no. 4, pp. 802–823, 2014.
  12. M. B. Synnestvedt, C. Chen, and J. H. Holmes, “CiteSpace II: Visualization and knowledge discovery in bibliographic databases,” AMIA Annual Symposium Proceedings, pp. 724–728, 2005.
  13. X. Yang, Y. Guo, Y. Liu, and H. Steck, “A survey of collaborative filtering based social recommender systems,” Computer Communications, vol. 41, pp. 1–10, 2014.
  14. Y. Koren, R. Bell, and C. Volinsky, “Matrix factorization techniques for recommender systems,” Computer, vol. 42, no. 8, pp. 30–37, 2009.
  15. T. Kanwal, A. M. Alhanjouri, S. U. Hassan, and N. Ikram, “Research paper recommendation system based on multiple features from citation network,” Scientometrics, 2024.
  16. J. D. West, I. Wesley-Smith, and C. T. Bergstrom, “A recommendation system based on hierarchical clustering of an article-level citation network,” IEEE Transactions on Big Data, vol. 2, no. 2, pp. 113–123, 2016.
  17. W. Li, H. Li, and Y. Zhang, “Scientific paper recommender system using deep learning and link prediction in citation network,” Heliyon, vol. 10, no. 15, 2024, Art. no. e34685.
  18. M. A. Abbas, S. Ajayi, M. Bilal, A. Oyegoke, M. Pasha, and H. T. Ali, “A deep learning approach for context-aware citation recommendation,” Journal of Ambient Intelligence and Humanized Computing, vol. 15, pp. 419–433, 2024.
  19. I. Pinedo, M. Larrañaga, and A. Arruarte, “Recent advances and trends in research paper recommender systems: A comprehensive survey,” arXiv preprint arXiv:2508.08828, 2025.
  20. K. Liu, Y. Zhang, R. Pan, T. Gao, and H. Wang, “Academic literature recommendation in large-scale citation networks enhanced by large language models,” arXiv preprint arXiv:2503.01189, 2025.