Adaptive Graph Neural Network with Cross-Source Attention and Dynamic Hyperparameter Regulation for Structured Modeling of Multi-Source Literary Corpora
Abstract
This paper proposes an adaptive graph neural network framework integrating cross-source attention and dynamic hyperparameter regulation for structured modeling of multi-source literary corpora. The dataset includes four genres—ancient books, modern novels, online literature, and bilingual translations—comprising about two million tokens across 18,000 chapters. Experiments on an NVIDIA RTX 3090 show that the proposed model achieves an average accuracy of 91.7%, macro F1 of 90.2%, and RMSE of 0.142, outperforming the fixed-parameter baseline by approximately 4%. The convergence speed improves by 20%, and robustness is maintained under small-scale, noisy, and cross-language conditions. Ablation results confirm the independent contribution of each module. The proposed mechanism achieves an effective balance between performance and efficiency, offering a reproducible and scalable approach for digital humanities and cross-disciplinary text analysis.References
Wang C, Liu X, Chen Z, et al. DeepStruct: Pretraining of language models for structure prediction[J]. arXiv preprint arXiv:2205.10475, 2022.https://doi.org/10.48550/arXiv.2205.10475
Deng S, Mao S, Zhang N, et al. SPEECH: Structured prediction with energy-based event-centric hyperspheres[J]. arXiv preprint arXiv:2305.13617, 2023.https://doi.org/10.48550/arXiv.2305.13617
Li X, Li J. Angle-optimized text embeddings[J]. arXiv preprint arXiv:2309.12871, 2023.https://doi.org/10.48550/arXiv.2309.12871
Nguyen T, Zhang Q, Yang B, et al. Predicting from Strings: Language Model Embeddings for Bayesian Optimization[J]. arXiv preprint arXiv:2410.10190, 2024.https://doi.org/10.48550/arXiv.2410.10190
Perri V, Qarkaxhija L, Zehe A, et al. One graph to rule them all: Using nlp and graph neural networks to analyse tolkien's legendarium[J]. arXiv preprint arXiv:2210.07871, 2022.https://doi.org/10.48550/arXiv.2210.07871
Zhao H, Xie J, Yan Y, et al. A corpus for named entity recognition in Chinese novels with multi-genres[J]. arXiv preprint arXiv:2311.15509, 2023.https://doi.org/10.48550/arXiv.2311.15509
Ke S, Montiel Olea J L, Nesbit J. Robust machine learning algorithms for text analysis[J]. Quantitative Economics, 2024, 15(4): 939-970.https://doi.org/10.3982/QE1825
Huang S, Yang K, Qi S, et al. When large language model meets optimization[J]. Swarm and Evolutionary Computation, 2024, 90: 101663.https://doi.org/10.1016/j.swevo.2024.101663
Das L, Ahuja L, Pandey A. A novel deep learning model-based optimization algorithm for text message spam detection: L Das et al[J]. The Journal of Supercomputing, 2024, 80(12): 17823-17848.https://doi.org/10.1007/s11227-024-06148-z
Wang L, Yang N, Huang X, et al. Improving text embeddings with large language models[J]. arXiv preprint arXiv:2401.00368, 2023.https://doi.org/10.48550/arXiv.2401.00368
Wang K, Ding Y, Han S C. Graph neural networks for text classification: A survey[J]. Artificial intelligence review, 2024, 57(8): 190.https://doi.org/10.1007/s10462-024-10808-0
Xu Y, Mao C, Wang Z, et al. Semantic-enhanced graph neural network for named entity recognition in ancient Chinese books[J]. Scientific Reports, 2024, 14(1): 17488.https://doi.org/10.1038/s41598-024-68561-x
Lu Z, Xie Q, Wang B, et al. Word grounded graph convolutional network[J]. arXiv preprint arXiv:2305.06434, 2023.https://doi.org/10.48550/arXiv.2305.06434
Dai Q. Construction of English and American literature corpus based on machine learning algorithm[J]. Computational Intelligence and Neuroscience, 2022, 2022(1): 9773452.https://doi.org/10.1155/2022/9773452
Sobchuk O, Šeļa A. Computational thematics: comparing algorithms for clustering the genres of literary fiction[J]. Humanities and Social Sciences Communications, 2024, 11(1): 1-12.https://doi.org/10.1057/s41599-024-02933-6
Tripto N I, Ali M E. The word2vec graph model for author attribution and genre detection in literary analysis[J]. arXiv preprint arXiv:2310.16972, 2023.https://doi.org/10.48550/arXiv.2310.16972
Hatzel H O, Stiemer H, Biemann C, et al. Machine learning in computational literary studies[J]. it-Information Technology, 2023, 65(4-5): 200-217.https://doi.org/10.1515/itit-2023-0041
Yang C, Wang X, Lu Y, et al. Large language models as optimizers[C]//The Twelfth International Conference on Learning Representations. 2023.https://doi.org/10.48550/arXiv.2309.03409
DOI:
https://doi.org/10.31449/inf.v49i27.12021Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
