Graph neural networks in the development of the theory of semantic-associative analysis of text data

 The article discusses the role of graph neural networks (GNNs) as a new
computational tool in the development of the theory of semantic-associative analysis of text data. GNNs allow us to formalize associative connections between lexical and conceptual units in the form of dynamic semantic graphs, which brings machine models of language processing
closer to the cognitive mechanisms of human thinking. A conceptual architecture based on Graph Attention Networks is proposed, integrating linguistic dependencies and external semantic knowledge, which ensures contextual adaptation and interpretability of the analysis.
The theoretical contribution of GNN to overcoming the limitations of traditional statistical and vector models is substantiated: the transition from isolated representations of words to modeling the spread of semantic activation through a network of associations. The results of preliminary
experiments (based on synthetic data and the RuSentiment corpus) demonstrate an increase in the accuracy of semantic classification and interpretability of conclusions. The article contributes to the interdisciplinary synthesis of computational linguistics, cognitive science, and machine learning, paving the way for the construction of computable theories of meaning generation in texts.

1. Leontiev A. A. Fundamentals of psycholinguistics / A. A. Leontiev. Moscow: Smysl Publishing House, 1997. 288 p.

2. Anderson J.R. Architecture of cognition. — Harvard University Press, 1983. — 318 p.

3. Church K. U., Hanks P. Norms of word association, mutual information and lexicography // Computational linguistics. — 1990. — Volume 16, No. 1. — pp. 22-29.

4. Speer R., Lowry-Duda J. ConceptNet at the SemEval-2017 seminar Task 2 // Proceedings of the 11th International Seminar on Semantic Assessment. - 2017. - pp. 115-121.

5. Russian associative dictionary / edited by Yu. N. Karaulov. — M.: AST, 2001-2003. — Vol. 1-4.

6. Zhou J. and others . Neural networks on graphs: an overview of methods and applications // AI Open. — 2020. — Volume 1. — pp. 57-81.

7. Kipf T.N., Welling M. Semi-controlled classification using graph convolutional networks // ICLR. — 2017. - 14 p.

8. Velichkovich P. et al. Graphic networks of attention // ICLR. - 2018. — 13 p.

9. Hamilton W. et al. Inductive representation learning on large graphs // NeurIPS, 2017, pp. 1024-1034.

10. Wu Z., Pan S., Chen F., et al. A comprehensive survey on graph neural networks // IEEE Transactions on Neural Networks and Learning Systems. — 2021. — Vol. 32, № 1. — P. 4–24.

11. Liu Y., Ott M., Goyal N., et al. RoBERTa: A robustly optimized BERT pretraining approach // arXiv preprint arXiv:1907.11692. — 2019.

12. Yao L., Mao C., Luo Y. Graph convolutional networks for text classification // Proceedings of the AAAI Conference on Artificial Intelligence. — 2019. — Vol. 33, № 1. — P. 7370–7377.

13. Speer R., Chin J., Havasi C. ConceptNet 5.5: An open multilingual graph of general knowledge // Proceedings of the AAAI Conference on Artificial Intelligence. — 2017. — Vol. 31, № 1.

14. Zhang Z., Han X., Liu Z., et al. ERNIE: Enhanced language representation with informative entities // Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. — 2019. — P. 1441–1451.

15. Ying Z., Bourgeois D., You J., et al. GNNExplainer: Generating explanations for graph neural networks // Advances in Neural Information Processing Systems. — 2019. — Vol. 32.

16. Yuan H., Yu H., Gui S., Ji S. Explainability in graph neural networks: A taxonomic survey // IEEE Transactions on Pattern Analysis and Machine Intelligence. — 2023. — Vol. 45, № 5. — P. 5674–5695.

17. Collins A. M., Loftus E. F. A spreading-activation theory of semantic processing // Psychological Review. — 1975. — Vol. 82, № 6. — P. 407–428.

18. Borge-Holthoefer J., Moreno Y. Structural and dynamical aspects of semantic networks: A review // Physics of Life Reviews. — 2022. — Vol. 40. — P. 1–25.

19. Loukachevitch N., Rubtsova Y., Ivanov V. RuSentiment: An extended sentiment collection for social media texts in Russian // Proceedings of the International Conference on Analysis of Images, Social Networks and Texts. — 2016. — P. 263–275.

20. Artemova E., Kuzmenko E., Rubtsova Y., et al. Targeted sentiment analysis in Russian: RuSentNE evaluation overview // Computational Linguistics and Intellectual Technologies Papers (Dialogue). — 2021. — Vol. 20. — P. 45–59.