Fine-Tuning Topic Modelling: A Coherence-Focused Analysis of Correlated Topic Models
DOI:
https://doi.org/10.60084/ijds.v2i2.236Keywords:
Topic modelling, Correlated Topic Model, Topic coherence, Optimization, Learning rateAbstract
The Correlated Topic Model (CTM) is a widely used approach for topic modelling that accounts for correlations among topics. This study investigates the effects of hyperparameter tuning on the model's ability to extract meaningful themes from a corpus of unstructured text. Key hyperparameters examined include learning rates (0.1, 0.01, 0.001), the number of topics (3, 5, 7, 10), and the number of top words (10, 20, 30, 40, 50, 80, 100). The Adam optimizer was used for model training, and performance was evaluated using the coherence score (c_v), a metric that assesses the interpretability and coherence of the generated topics. The dataset comprised 100 articles, and results were visualized using line plots and heatmaps to highlight performance trends. The highest coherence score of 0.803 was achieved with three topics and 10 top words. The findings demonstrate that fine-tuning hyperparameters significantly improves the model's ability to generate coherent and interpretable topics, resulting in more accurate and insightful outcomes. This research underscores the importance of parameter optimization in enhancing the effectiveness of CTM for topic modelling applications.
Downloads
References
- Kherwa, P., and Bansal, P. (2018). Topic Modeling: A Comprehensive Review, ICST Transactions on Scalable Information Systems, 159623. doi:10.4108/eai.13-7-2018.159623.
- Vayansky, I., and Kumar, S. A. P. (2020). A Review of Topic Modeling Methods, Information Systems, Vol. 94, 101582. doi:10.1016/j.is.2020.101582.
- Qiang, J., Qian, Z., Li, Y., Yuan, Y., and Wu, X. (2022). Short Text Topic Modeling Techniques, Applications, and Performance: A Survey, IEEE Transactions on Knowledge and Data Engineering, Vol. 34, No. 3, 1427–1445. doi:10.1109/TKDE.2020.2992485.
- Xun, G., Li, Y., Zhao, W. X., Gao, J., and Zhang, A. (2017). A Correlated Topic Model Using Word Embeddings, IJCAI (Vol. 17), 4207–4213.
- Mol, M. J., Belfi, B., and Bakk, Z. (2024). Unravelling the Skills of Data Scientists: A Text Mining Analysis of Dutch University Master Programs in Data Science and Artificial Intelligence, PLoS ONE, Vol. 19, No. 2 February, 1–14. doi:10.1371/journal.pone.0299327.
- Koltcov, S., Ignatenko, V., Boukhers, Z., and Staab, S. (2020). Analyzing the Influence of Hyper-Parameters and Regularizers of Topic Modeling in Terms of Renyi Entropy, Entropy, Vol. 22, No. 4. doi:10.3390/E22040394.
- Ford, J. D., Elhai, J. D., Marengo, D., Almquist, Z., Olff, M., Spiro, E. S., and Armour, C. (2022). Temporal Trends in Health Worker Social Media Communication during the COVID – 19 Pandemic, No. August, 1–16. doi:10.1002/nur.22266.
- Koltcov, S., Ignatenko, V., Terpilovskii, M., and Rosso, P. (2021). Analysis and Tuning of Hierarchical Topic Models Based on Renyi Entropy Approach, PeerJ Computer Science, Vol. 7, 1–35. doi:10.7717/PEERJ-CS.608.
- Shao, Y., Wang, J., Sun, H., Yu, H., Xing, L., Zhao, Q., and Zhang, L. (2024). An Improved BGE-Adam Optimization Algorithm Based on Entropy Weighting and Adaptive Gradient Strategy, Symmetry, Vol. 16, No. 5, 1–16. doi:10.3390/sym16050623.
- Sun, H., Yu, H., Shao, Y., Wang, J., Xing, L., Zhang, L., and Zhao, Q. (2024). An Improved Adam’s Algorithm for Stomach Image Classification, Algorithms, Vol. 17, No. 7, 1–13. doi:10.3390/a17070272.
- Shao, Y., Yang, J., Zhou, W., Sun, H., Xing, L., Zhao, Q., and Zhang, L. (2024). An Improvement of Adam Based on a Cyclic Exponential Decay Learning Rate and Gradient Norm Constraints.
- Wang, A., Liu, W., and Liu, Z. (2022). A Two-Sample Robust Bayesian Mendelian Randomization Method Accounting for Linkage Disequilibrium and Idiosyncratic Pleiotropy with Applications to the COVID-19 Outcomes, Genetic Epidemiology, Vol. 46, Nos. 3–4, 159–169. doi:10.1002/gepi.22445.
- Chérief-Abdellatif, B. E. (2018). Consistency of ELBO Maximization for Model Selection, Proceedings of Machine Learning Research, Vol. 96, No. 1974, 11–31.
- Wijanto, M. C., Widiastuti, I., and Yong, H.-S. (2024). Topic Modeling for Scientific Articles: Exploring Optimal Hyperparameter Tuning in BERT., International Journal on Advanced Science, Engineering & Information Technology, Vol. 14, No. 3.
- Szigeti, Á., Frank, R., and Kiss, T. (2024). Contribution to the Harm Assessment of Darknet Markets: Topic Modelling Drug Reviews on Dark0de Reborn, Crime Science, Vol. 13, No. 1, 1–10. doi:10.1186/s40163-024-00211-z.
- Nguyen, H., and Hovy, D. (2019). Hey Siri. OK Google. Alexa: A Topic Modeling of User Reviews for Smart Speakers, W-NUT@EMNLP 2019 - 5th Workshop on Noisy User-Generated Text, Proceedings, 76–83. doi:10.18653/v1/d19-5510.
- Chandra, R., and Ranjan, M. (2022). Artificial Intelligence for Topic Modelling in Hindu Philosophy: Mapping Themes between the Upanishads and the Bhagavad Gita, PLoS ONE, Vol. 17. doi:10.1371/journal.pone.0273476.
- Tijare, P., and Jhansi Rani, P. (2020). Exploring Popular Topic Models, Journal of Physics: Conference Series, Vol. 1706, No. 1, 012171. doi:10.1088/1742-6596/1706/1/012171.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Syahrial Syahrial, Razief Perucha Fauzie Afidh
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.