Automated comparison of scientific research based on academic genealogy
https://doi.org/10.32517/0234-0453-2025-40-6-16-27
Abstract
The article addresses the problem of analyzing large corpora of scientific texts. It is noted that traditional scientometric approaches based on citation analysis do not always capture the substantive proximity of ideas or trace the intellectual continuity of scientific knowledge. The paper proposes an algorithm that combines the capabilities of large language models (LLMs) with quantitative analytical methods. The approach proceeds in two stages. At the first stage, LLM is used to automatically structure the text of a scientific paper and convert it into a machine-readable format. This yields, for each work, a vector representation of its thematic profile. At the second stage, thematic profiles of individual works and of pre-specified groups (schools of thought) are compared using centroid distances and clustering techniques. The ultimate goal is to move beyond formal relational analyses among researchers (e. g., “supervisor — dissertation candidate”) toward constructing an intellectual genealogy that tracks the evolution of schools of thought on the basis of the substantive proximity of their ideas. It is emphasized that the proposed approach does not replace expert assessment but serves as an auxiliary tool for navigating the scientific literature and identifying connections between studies.
Keywords
About the Authors
A. Kh. MarinosyanRussian Federation
Andreas Kh. Marinosyan, postgraduate student
Institute of Digital Education; Department of Education Informatisation
Moscow
S. G. Grigoriev
Russian Federation
Sergey G. Grigoriev, Corresponding Member of the RAE, Doctor of Sciences (Engineering), Professor, Professor at the Department
Institute of Digital Education; Department of IT, Management and Technology
Moscow
I. M. Lerner
Russian Federation
Ilya M. Lerner, Doctor of Sciences (Engineering), Professor, Professor at the
Department
Institute of Radio Electronics, Photonics and Digital Technologies; Department of Nanotechnology in Electronics; Institute of Physics; Department of Radio Astronomy
The Republic of Tatarstan; Kazan
M. A. Anikieva
Russian Federation
Marina A. Anikieva, Candidate of Sciences (Engineering), Associate Professor
School of Space and Information Technology; Department of Artificial Intelligence Systems
Krasnoyarsk
References
1. Grigoriev S. G., Lerner I. M., Marinosyan A. Kh., Arutyunova N. K., Grigorieva M. A. On the issue of educational and methodological information selection for implementing an adaptive learning management system: Algorithm of a priori authors classification. Informatics and Education. 2025;40(2):66–78. (In Russian.) EDN: YDTFTG. DOI: 10.32517/0234-0453-2025-40-2-66-78.
2. Grigoriev S. G., Lerner I. M., Marinosyan A. Kh., Grigorieva M. A. On the issue of educational and methodological information selection for implementing an adaptive learning management system: Algorithm of selecting authors of literature taking into account the emotional and psychological characteristics of users based on the ideas of academic genealogy. Informatics and Education. 2025;40(3):69–79. (In Russian.) EDN: DVPEUJ. DOI: 10.32517/0234-0453-2025-40-3-69-79.
3. Lerner I. M., Marinosyan A. Kh., Grigoriev S. G., Yusupov A. R., Anikieva M. A., Garifullina G. A. An approach to the formation of intellectual academic genealogy using large language models. Electromagnetic Waves and Electronic Systems. 2024;29(4):108–120. (In Russian.) EDN: BSNYZW. DOI: 10.18127/j5604128-202404-09.
4. de Solla Price D. J., Beaver D. Collaboration in an invisible college. American Psychologist. 1966;21(11):1011–1018. DOI: 10.1037/h0024051.
5. Gallon M., Law J., Rip A. (Eds) Mapping the dynamics of science and technology: Sociology of Science in the Real World. Houndmills: Macmillan Press; 1986. 242 p.
6. Salton G., Wong A., Yang C. S. A vector space model for automatic indexing. Communications of the ACM. 1975;18(11):613–620. DOI: 10.1145/361219.361220.
7. Lu Yonghe, Li Yanfeng. Improvement of text feature weighting method based on TF-IDF algorithm. Library and Information Service. 2013;57(3):90–95. (In Chinese.)
8. Herlocker J. L., Konstan J. A., Terveen L. G., Riedl J. T. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems. 2004;1(22):5–53. DOI: 10.1145/963770.963772.
9. Ji W., Liu S., Song Y., Qi J. Research of Intelligent recommendation system based on the user and association rules mining for books. Proc. 2015 5<sup>th</sup> Int.Conf. on Computer Sciences and Automation Engineering. Atlantis Press; 2016:294–299. DOI: 10.2991/iccsae-15.2016.56.
10. Yao Y. Library resource vertical search engine based on ontology. 2017 Int. Conf. on Smart Grid and Electrical Automation (ICSGEA). IEEE, Changsha, China; 2017:672–675. DOI: 10.1109/ICSGEA.2017.159.
11. Blei D. M., Ng A. Y., Jordan M. I. Latent Dirichlet allocation. Journal of Machine Learning Research. 2003;3:993–1022.
12. Griffiths T. L., Steyvers M. Finding scientific topics. Proc. of the National Academy of Sciences. 2004;101(suppl_1):5228–5235. DOI: 10.1073/pnas.0307752101.
13. Asmussen C. B., Møller C. Smart literature review : A practical topic modelling approach to exploratory literature review. Journal of Big Data. 2019;6(1):1–18. DOI: 10.1186/s40537-019-0255-7.
14. Blei D. M., Lafferty J. D. Dynamic topic models. ICML ‘06: Proc. 23<sup>rd</sup> Int. Conf. on Machine Learning. New York, Association for Computing Machinery; 2006:113–120. DOI: 10.1145/1143844.1143859.
15. Beltagy I., Lo K., Cohan A. SciBERT: A pretrained language model for scientific text. Proc. 2019 Conf. on Empirical Methods in Natural Language Processing and the 9<sup>th</sup> Int. Joint Conf. on Natural Language Processing (EMNLP— IJCNLP). Kerrville, TX, Association for Computational Linguistics; 2019:3615–3620. DOI: 10.18653/v1/D19-1371.
16. Hogan A., Blomqvist E., Cochez M., d’Amato C., Melo G. D., Gutierrez C., Kirrane S., Gayo J. E. L., Navigli R., Neumaier S., Ngomo A. C. N. Knowledge graphs. ACM Computing Surveys (CSUR). 2021;54(4):1–37. DOI: 10.1145/3447772.
17. Auer S., Oelen A., Haris M., Stocker M., D’Souza J., Farfar K. E., Vogt L., Prinz M., Wiens V., Jaradeh M. Y., Improving access to scientific literature with knowledge graphs. Bibliothek Forschung und Praxis. 2020;44(3):516–529. DOI: 10.1515/bfp-2020-2042.
18. Himmelstein D. S., Lizee A., Hessler C., Brueggeman L., Chen S. L., Hadley D., Green A., Khankhanian P., Baranzini S. E. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife. 2020;6(e26726). DOI: 10.7554/eLife.26726.
19. Gurianov V. I., Elizarov A. M. Software module for forming digital mathematical space based on knowledge graphs. Russian Digital Libraries Journal. 2025;28(3):622–639. (In Russian.) EDN: PEVYAR. DOI: 10.26907/1562-5419-2025-28-3-622-639.
20. Shamsabadi S., D’Souza J., Auer S. Large language models for scientific information extraction: An empirical study for virology. Findings of the Association for Computational Linguistics: EACL 2024. Kerrville, TX, Association for Computational Linguistics; 2024:374–392.
21. Taylor R., Kardas M., Cucurull G., Scialom T., Hartshorn A., Saravia E., Poulton A., Kerkez V., Stojnic R. Galactica: A large language model for science. arXiv preprint. 2022:2211.09085.
22. Bespalko V. P. Programmed learning. Didactic foundations. Moscow, Vysshaya shkola; 1970. 296 p. (In Russian.) EDN: ZHYULR.
23. Anderson M. J. A new method for non-parametric multivariate analysis of variance. Austral Ecology. 2001;26(1):32–46. DOI: 10.1111/j.1442-9993.2001.01070.pp.x.
24. Rousseeuw P. J. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics. 1987;20:53–65. DOI: 10.1016/0377-0427(87)90125-7.
Review
For citations:
Marinosyan A.Kh., Grigoriev S.G., Lerner I.M., Anikieva M.A. Automated comparison of scientific research based on academic genealogy. Informatics and education. 2025;40(6):16-27. (In Russ.) https://doi.org/10.32517/0234-0453-2025-40-6-16-27























