Topic Modeling Analysis of BIM Research Across Design,  Construction,  and Operation Phases: A 25-Year Time-Series Study Using LDA and BERTopic

Baek-Jun Kim; Kweon-Hyoung Lee

doi:10.13161/kibim.2025.15.4.010

All Issue

2025 Vol.15, Issue 4 Preview Page Next Page

Research Article

Topic Modeling Analysis of BIM Research Across Design, Construction, and Operation Phases: A 25-Year Time-Series Study Using LDA and BERTopic BIM 연구의 설계･시공･운영 단계별 토픽 모델링 분석: LDA와 BERTopic을 활용한 25년 시계열 연구동향 탐색

31 December 2025. pp. 10-23

PDF XML

Abstract

This study analyzes the 25-year evolution of Building Information Modeling (BIM) research across design, construction, and operation phases through an integrated text mining framework combining Latent Dirichlet Allocation (LDA) and BERTopic methodologies. We examined 11,924 papers collected from the Korean Citation Index (KCI) and ScienceDirect databases spanning 2000~2024. The analysis reveals distinct developmental trajectories between research contexts: domestic studies demonstrate gradual, standards- based advancement with systematic phase expansion, while international research exhibits rapid innovation characterized by AI integration and digital twin convergence. Phase-based keyword analysis shows progressive expansion from design-centric applications to comprehensive construction and operation implementations. BERTopic clustering analysis indicates that domestic research maintains specialized topic segmentation with clear disciplinary boundaries, whereas international studies display highly interconnected thematic networks reflecting multidisciplinary integration. This study contributes a novel dual-methodology framework that systematically integrates temporal topic modeling with semantic clustering analysis, providing empirical insights for understanding BIM research evolution patterns and informing future research directions and policy development strategies.

Keywords

Building Information Modeling (BIM)

Latent Dirichlet Allocation (LDA)

Technological Application Structure

Semantic Clustering

키워드

BIM

LDA

BERTopic

기술 응용 구조

의미 기반 클러스터

References

Bastian, M., Heymann, S., Jacomy, M. (2009). Gephi: An open Source Software for Exploring and Manipulating Networks, Proceedings of ICWSM, 3, pp. 361-362.

10.1609/icwsm.v3i1.13937

Blei, D. M., Lafferty, J. D. (2006). Dynamic Topic Models. ICML ‘06 Proceedings, pp. 113-120.

10.1145/1143844.1143859

Blei, D. M., Ng, A. Y., Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, pp. 993-1022.

Devlin, J., Chang, M. W., Lee, K., Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1, pp. 4171-4186.

10.18653/v1/N19-1423

Grootendorst, M. (2022). BERTopic: Neural Topic Modeling with a Class-based TF-IDF Procedure. arXiv preprint, arXiv:2203.05794.

Kang, S. M. (2024). Convergent Development of BIM Technology and Digital Transformation in Construction Industry, Journal of the Korea Institute of Building Construction Management, 25(3), pp. 45-58.

Kim, S. M., Lee, S. K. (2023). Keyword Network Analysis of BIM Research Trends Based on Web of Science, Journal of the Korea Institute of Building Construction, 23(4), pp. 387-398.

Park, Y.-M. (2020). Classification of tax Q&A using LDA topic modeling and BERT, Master’s Thesis, Korea University, pp. 13-16.

Reimers, N., Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP- IJCNLP 2019 Proceedings, pp. 3982-3992.

10.18653/v1/D19-1410

Röder, M., Both, A., Hinneburg, A. (2015). Exploring the Space of Topic Coherence Measures. WSDM ‘15 Proceedings, pp. 399-408.

10.1145/2684822.2685324

Saka, A. B., Chan, D. W. M. (2019). A Scientometric Review and Metasynthesis of BIM Research in Africa. Buildings, 9(4), 85. https://doi.org/10.3390/buildings9040085

10.3390/buildings9040085

Santos, R., Costa, A. A., Grilo, A. (2017). Bibliometric Analysis and Review of BIM literature, Automation in Construction, 80, pp. 118-136.

10.1016/j.autcon.2017.03.005

Yalcinkaya, M., Singh, V. (2015). Patterns and Trends in Building Information Modeling (BIM) Research: A Latent Semantic Analysis. Automation in Construction, 59, pp. 68-80.

10.1016/j.autcon.2015.07.012

Zhao, X. (2017). A Scientometric Review of Global BIM Research: Analysis and Visualization, Automation in Construction, 80, pp. 37-47.

10.1016/j.autcon.2017.04.002

Information

Publisher :Journal of KIBIM
Publisher(Ko) :한국BIM학회
Journal Title :Journal of KIBIM
Journal Title(Ko) :한국BIM학회논문집
Volume : 15
No :4
Pages :10-23
Received Date : 2025-08-25; 2025-10-31
Accepted Date : 2025-11-05
DOI :https://doi.org/10.13161/kibim.2025.15.4.010

Journal of KIBIM ISSN:2288-1697(Print) 2288-1697(Online) 한국BIM학회논문집

All Issue