Dynamic Knowledge Map of Artificial Intelligence Literature: Longitudinal Trend Analysis Using Latent Dirichlet Allocation

Aulia Khairunnisa; Syalwa Salsabillah Siregar; Ken Ditha Tania; Allsela Meiriza; Zaqqi Yamani; Shanti Dewi Siawanta

doi:10.34148/teknika.v15i2.1470

Authors

Aulia Khairunnisa Information System, Faculty of Computer Science, Universitas Sriwijaya, Palembang, South Sumatra, Indonesia
Syalwa Salsabillah Siregar Information System, Faculty of Computer Science, Universitas Sriwijaya, Palembang, South Sumatra, Indonesia
Ken Ditha Tania Information System, Faculty of Computer Science, Universitas Sriwijaya, Palembang, South Sumatra, Indonesia
Allsela Meiriza Information System, Faculty of Computer Science, Universitas Sriwijaya, Palembang, South Sumatra, Indonesia
Zaqqi Yamani Information System, Faculty of Computer Science, Universitas Sriwijaya, Palembang, South Sumatra, Indonesia
Shanti Dewi Siawanta School of Computer Science, Faculty of Science, University of Nottingham, Nottingham, Nottinghamshire, United Kingdom

DOI:

https://doi.org/10.34148/teknika.v15i2.1470

Keywords:

Artificial Intelligence, Knowledge Mapping, Latent Dirichlet Allocation, Research Trend Mapping, Topic Modeling

Abstract

The rapid growth of Artificial Intelligence (AI) publications has increased the complexity of identifying thematic structures and understanding the evolution of research trends. Conventional citation-based bibliometric approaches are often limited in capturing semantic relationships within large-scale textual data. This study aims to analyze the knowledge structure and longitudinal dynamics of AI literature using a topic modeling approach within a knowledge mapping framework. The dataset consists of publication abstracts from the arXiv repository spanning 2015–2024, and the Latent Dirichlet Allocation (LDA) algorithm is employed with coherence-based evaluation to extract latent topics. The results indicate that the optimal model configuration consists of nine topic clusters, achieving a peak coherence score of 0.4605. Longitudinal analysis suggests a notable shift in research focus after 2021, marked by the rapid growth of Large Language Models (LLMs) and generative AI. This shift reflects a process of thematic integration, where foundational areas such as deep learning architectures are increasingly incorporated into more advanced domains. In addition, topics such as Graph Neural Networks (GNNs) exhibit relatively stable trends, which may indicate technological maturity rather than a decline in relevance. Overall, the findings provide data-driven insights into the evolving landscape of AI research and may support researchers and institutions in identifying emerging research directions within the scope of the analyzed dataset.

Downloads

Download data is not yet available.

References

[1] A. Ayaz, A. K. Kabakuş, Ü. Özen, Ö. Alkan, and S. Aydın, “Topic modelling of contemporary management information systems research: a latent dirichlet allocation approach Topic Modelling of Contemporary Management Information Systems Research: A Latent Dirichlet Allocation Approach 1,” 2025. [Online]. Available: https://orcid.org/0000-0002-3814-3539.

[2] A. K. W. Weng, H. Y. Chang, K. K. Lai, and Y. B. Lin, “Topic Modeling on Peer Interaction in Online and Mobile Learning of Higher Education: 1993–2022,” Aug. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/educsci14080867.

[3] A. Abdelrazek, Y. Eid, E. Gawish, W. Medhat, and A. Hassan, “Topic modeling algorithms and applications: A survey,” Inf. Syst., vol. 112, p. 102131, Feb. 2023, doi: 10.1016/j.is.2022.102131.

[4] Y. J. Jung and Y. Kim, “Research trends of sustainability and marketing research, 2010–2020: Topic modeling analysis,” Heliyon, vol. 9, no. 3, Mar. 2023, doi: 10.1016/j.heliyon.2023.e14208.

[5] X. Shu and Y. Ye, “Knowledge Discovery: Methods from data mining and machine learning,” Soc. Sci. Res., vol. 110, p. 102817, 2023, doi: https://doi.org/10.1016/j.ssresearch.2022.102817.

[6] T. Dillan and D. H. Fudholi, “LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking,” IEEE Access, vol. 11, pp. 59142–59163, 2023, doi: 10.1109/ACCESS.2023.3285116.

[7] R. K. Gupta, R. Agarwalla, B. H. Naik, J. R. Evuri, A. Thapa, and T. D. Singh, “Prediction of research trends using LDA based topic modeling,” Global Transitions Proceedings, vol. 3, no. 1, pp. 298–304, Jun. 2022, doi: 10.1016/j.gltp.2022.03.015.

[8] Y. Pamungkas, “Leveraging Topic Modelling to Analyze Biomedical Research Trends from the PubMed Database Using LDA Method,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 13, no. 2, pp. 237–244, Jun. 2024, doi: 10.32736/sisfokom.v13i2.2117.

[9] R. Egger and J. Yu, “A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts,” Frontiers in Sociology, vol. 7, May 2022, doi: 10.3389/fsoc.2022.886498.

[10] Nursyahrina, S. Defit, and R. Sovia, “Metode BERTopic dan LDA untuk Analisis Tren Penelitian Bidang Ilmu Komputer,” Jurnal KomtekInfo, pp. 332–341, Sep. 2024, doi: 10.35134/komtekinfo.v11i4.580.

[11] R. G. Dalimunthe and R. A. Putri, “Pemetaan Topik Tugas Akhir Program Studi Ilmu Komputer Menggunakan Algoritma Latent Dirichlet Allocation,” Journal of Computer System and Informatics (JoSYC), vol. 5, no. 4, pp. 921–932, Aug. 2024, doi: 10.47065/josyc.v5i4.5759.

[12] V. Maphosa and M. Maphosa, “Artificial intelligence in higher education: a bibliometric analysis and topic modeling approach,” Applied Artificial Intelligence, vol. 37, no. 1, 2023, doi: 10.1080/08839514.2023.2261730.

[13] A. Farea, S. Tripathi, G. Glazko, and F. Emmert-Streib, “Investigating the optimal number of topics by advanced text-mining techniques: Sustainable energy research,” Eng. Appl. Artif. Intell., vol. 136, Oct. 2024, doi: 10.1016/j.engappai.2024.108877.

[14] Sumit Mishra, “arXiv Scientific Research Paper Dataset,” Feb. 2025. Accessed: Mar. 04, 2026. [Online]. Available: https://data.mendeley.com/datasets/mm6kst3krj/1

[15] U. Detthamrong et al., “Topic Modeling Analytics of Digital Economy Research: Trends and Insights,” Journal of Scientometric Research, vol. 13, no. 2, pp. 448–458, May 2024, doi: 10.5530/jscires.13.2.35.

[16] D. Yu and B. Xiang, “Discovering topics and trends in the field of Artificial Intelligence: Using LDA topic modeling,” Expert Syst. Appl., vol. 225, p. 120114, 2023, doi: https://doi.org/10.1016/j.eswa.2023.120114.

[17] L. Sun and Y. Yin, “Discovering themes and trends in transportation research using topic modeling,” Transp. Res. Part C Emerg. Technol., vol. 77, pp. 49–66, 2017, doi: https://doi.org/10.1016/j.trc.2017.01.013.

[18] L. Zhu and D. Luo, “A Novel Efficient and Effective Preprocessing Algorithm for Text Classification,” Journal of Computer and Communications, vol. 11, no. 03, pp. 1–14, 2023, doi: 10.4236/jcc.2023.113001.

[19] R. P. F. Afidh and Syahrial, “Pemodelan Topik Menggunakan n-Gram dan Non-negative Matrix Factorization,” Jurnal Informasi dan Teknologi, pp. 265–275, Sep. 2023, doi: 10.60083/jidt.v5i1.385.

[20] I. V. de Mendizabal, V. Basto-Fernandes, E. Ezpeleta, J. R. Méndez, S. Gómez-Meire, and U. Zurutuza, “Multi-objective evolutionary optimization for dimensionality reduction of texts represented by synsets,” PeerJ Comput. Sci., vol. 9, 2023, doi: 10.7717/peerj-cs.1240.

[21] D. M. Blei, A. Y. Ng, and J. B. Edu, “Latent Dirichlet Allocation Michael I. Jordan,” 2003.

[22] P. Upendra Dasu, E. A. Fox, and C. Xuan Wang Yinlin Chen, “Topic Modeling for Heterogeneous Digital Libraries: Tailored Approaches Using Large Language Models,” 2024.

[23] A. Amaro and F. Bacao, “Topic Modeling: A Consistent Framework for Comparative Studies,” Emerging Science Journal, vol. 8, no. 1, pp. 125–139, Feb. 2024, doi: 10.28991/ESJ-2024-08-01-09.

[24] M. Röder, A. Both, and A. Hinneburg, “Exploring the space of topic coherence measures,” in WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, Feb. 2015, pp. 399–408. doi: 10.1145/2684822.2685324.