{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:04:02Z","timestamp":1772550242497,"version":"3.50.1"},"reference-count":51,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Informatics"],"abstract":"<jats:p>Causal inference in text data has been a demanding objective in the field of natural language processing, mainly due to the intrinsic ambiguity and context sensitivity inherent in data, inducing uncertainty. Diminishing this uncertainty is essential in identifying reliable causal connections and advancing predictive consistency. In this research, we introduce an uncertainty-aware ensemble architecture that combines multiple text embedding schemes with both linear and nonlinear classifiers to boost causal text detection. Both sparse and neural-level embeddings were employed, and then combined it with an ensemble weighting approach based on two uncertainty estimation techniques, namely entropy-based and KL divergence-based. Unlike conventional ensemble methods with uniform or fixed voting strategies, our approach assigns weights inversely proportional to classifier uncertainty, ensuring that confident models exert greater influence on the final decisions. Our results show that TF-IDF, through its effective word frequency weighting scheme, consistently outperforms other embedding techniques, achieving better performance across both linear and nonlinear classifiers on both datasets (News Corpus and CausalLM\u2013Adjective group). The experimental results show that our uncertainty-aware ensemble approach enhances both calibration and confidence predictions. Entropy-based weighting improves confidence in the case of linear classifiers with accuracy, F1-score, entropy and prediction confidence values of 94.3%, 94.0%, 0.382 and 0.774, respectively, while in the case of nonlinear classifiers the KL divergence-based weighting acquires a better performance with an accuracy of 97.6%, F1-score of 97.2%, KL Mean value of around 0.055 and LogLoss of 0.221.<\/jats:p>","DOI":"10.3390\/informatics13030037","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T09:45:12Z","timestamp":1772531112000},"page":"37","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Causal Text Detection Using Uncertainty-Weighted Machine Learning Ensembles"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3759-5388","authenticated-orcid":false,"given":"Sivachandra","family":"K B","sequence":"first","affiliation":[{"name":"Amrita School of Artificial Intelligence, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, Ettimadai 641112, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4853-8670","authenticated-orcid":false,"given":"Neethu","family":"Mohan","sequence":"additional","affiliation":[{"name":"Amrita School of Artificial Intelligence, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, Ettimadai 641112, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6326-4068","authenticated-orcid":false,"given":"Mithun Kumar","family":"Kar","sequence":"additional","affiliation":[{"name":"Amrita School of Artificial Intelligence, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, Ettimadai 641112, India"}]},{"given":"Sikha","family":"O K","sequence":"additional","affiliation":[{"name":"BCN MEdTech, Department of Information and Communication Technologies, University of Pompeu Fabra, 08002 Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3298-0539","authenticated-orcid":false,"given":"Sachin Kumar","family":"S","sequence":"additional","affiliation":[{"name":"Amrita School of Artificial Intelligence, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, Ettimadai 641112, India"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"ref_1","unstructured":"Hu, M., Zhang, Z., Zhao, S., Huang, M., and Wu, B. (2023). Uncertainty in Natural Language Processing: Sources, Quantification, and Applications. arXiv."},{"key":"ref_2","unstructured":"Baan, J., Daheim, N., Ilia, E., Ulmer, D., Li, H.-S., Fern\u00e1ndez, R., Plank, B., Sennrich, R., Zerva, C., and Aziz, W. (2023). Uncertainty in Natural Language Generation: From Theory to Applications. arXiv."},{"key":"ref_3","first-page":"7322","article-title":"Quantifying Uncertainties in Natural Language Processing Tasks","volume":"33","author":"Xiao","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ulmer, D., Frellsen, J., and Hardmeier, C. (2022). Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity. Findings of the Association for Computational Linguistics: EMNLP 2022, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.findings-emnlp.198"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hu, Y., and Khan, L. (2021, January 14\u201318). Uncertainty-aware reliable text classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual.","DOI":"10.1145\/3447548.3467382"},{"key":"ref_6","unstructured":"Prasad, R., Dinesh, N., Lee, A., Miltsakaki, E., Robaldo, L., Joshi, A., and Webber, B. (June, January 26). The Penn Discourse TreeBank 2.0. Proceedings of the International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco."},{"key":"ref_7","unstructured":"Miwa, M., Thompson, P., and Ananiadou, S. (2012, January 23\u201325). BioCause: Annotating and analysing causal relations in the biomedical domain. Proceedings of the International Conference on Language Resources and Evaluation (LREC), Istanbul, Turkey."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hendrickx, I., Kim, S.N., Kozareva, Z., Semmar, N., Szpakowicz, S., and Zanzotto, F.M. (2010, January 15\u201316). SemEval-2010 Task 8: Multi-way classification of semantic relations between pairs of nominals. Proceedings of the 5th International Workshop on Semantic Evaluation (SemEval), Los Angeles, CA, USA.","DOI":"10.3115\/1621969.1621986"},{"key":"ref_9","unstructured":"Gao, T., Meng, Y., and Chen, D. (2021, January 1\u20136). CAUSALBERT: Injecting causal knowledge into pretrained language models for causal relation extraction. Proceedings of the Findings of the Association for Computational Linguistics (ACL), Virtual."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Girju, R. (2003, January 11). Automatic detection of causal relations for question answering. Proceedings of the ACL Workshop on Multilingual Summarization and Question Answering, Sapporo, Japan.","DOI":"10.3115\/1119312.1119322"},{"key":"ref_11","unstructured":"Straka, M., and Strakov\u00e1, J. (2016, January 23\u201328). UDPipe: Trainable pipeline for processing CoNLL-U files. Proceedings of the International Conference on Language Resources and Evaluation (LREC), Portoro\u017e, Slovenia."},{"key":"ref_12","unstructured":"Straka, M. (2018). UDPipe 2.0: Models and design. CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Association for Computational Linguistics."},{"key":"ref_13","unstructured":"Tan, F.A., H\u00fcrriyeto\u011flu, A., Caselli, T., Oostdijk, N., Nomoto, T., Hettiarachchi, H., Ameer, I., Uca, O., Liza, F.F., and Hu, T. (2022). The causal news corpus: Annotating causal relations in event sentences from news. arXiv."},{"key":"ref_14","unstructured":"Patel, R. (2023, January 7). Interosml@ causal news corpus 2023: Understanding causal relationships: Supervised contrastive learning for event classification. Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text, Varna, Bulgaria."},{"key":"ref_15","unstructured":"Schrader, T.P., Razniewski, S., Lange, L., and Friedrich, A. (2023). Boschai@ causal news corpus 2023: Robust cause-effect span extraction using multi-layer sequence tagging and data augmentation. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Burdisso, S., Zuluaga-Gomez, J., Villatoro-Tello, E., Fajcik, M., Singh, M., Smrz, P., and Motlicek, P. (2022). IDIAPers@ causal news corpus 2022: Efficient causal relation identification through a prompt-based few-shot approach. arXiv.","DOI":"10.18653\/v1\/2022.case-1.9"},{"key":"ref_17","unstructured":"Adibhatla, H.S., and Shrivastava, M. (2022, January 7\u20138). LTRC@ causal news corpus 2022: Extracting and identifying causal elements using adapters. Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events from Text (CASE), Abu Dhabi, United Arab Emirates."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jia, L., Yang, F., Man, K.L., Purwanto, E., Guan, S.-U., Smith, J., and Yue, Y. (2024). Quantify the Causes of Causal Emergence: Critical Conditions of Uncertainty and Asymmetry in Causal Structure. arXiv.","DOI":"10.2139\/ssrn.4366258"},{"key":"ref_19","unstructured":"Chau, S.L., Ton, J.-F., Gonz\u00e1lez, J., Teh, Y.W., and Sejdinovic, D. (2021). BAYESIMP: Uncertainty Quantification for Causal Data Fusion. Unpublished Manuscript\/Preprint, University of Oxford and Collaborators. arXiv."},{"key":"ref_20","unstructured":"Annadani, Y., Rothfuss, J., Lacoste, A., Scherrer, N., Goyal, A., Bengio, Y., and Bauer, S. (2021). Variational Causal Networks: Approximate Bayesian Inference over Causal Structures. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Morucci, M., Noor-E-Alam, M., and Rudin, C. (2022). A Robust Approach to Quantifying Uncertainty in Matching Problems of Causal Inference, Northeastern University. Technical Report.","DOI":"10.1287\/ijds.2022.0020"},{"key":"ref_22","unstructured":"Chaudhry, A., Xu, P., and Gu, Q. (2017, January 6\u201311). Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_23","unstructured":"Jesson, A., Mindermann, S., Shalit, U., and Gal, Y. (2020). Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Atmaja, B.T., Sasou, A., and Burkhardt, F. (2024). Uncertainty-Based Ensemble Learning for Speech Classification. Proceedings of the 27th Conference of the Oriental COCOSDA (O-COCOSDA), Hsinchu City, Taiwan, 17\u201319 October 2024, IEEE.","DOI":"10.1109\/O-COCOSDA64382.2024.10800111"},{"key":"ref_25","unstructured":"Ruan, Y., Singh, S., Morningstar, W., Alemi, A.A., Ioffe, S., Fischer, I., and Dillon, J.V. (2022). Weighted Ensemble Self-Supervised Learning. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2601","DOI":"10.17485\/IJST\/v16i33.85","article-title":"An Entropy Based Alternate Approach to Develop an Ensemble Classifier","volume":"16","author":"Sreeni","year":"2023","journal-title":"Indian J. Sci. Technol."},{"key":"ref_27","unstructured":"Wang, J., Xu, S., Duan, B., Liu, C., and Liang, J. (2017). An Ensemble Classification Algorithm Based on Information Entropy for Data Streams. arXiv."},{"key":"ref_28","first-page":"10730","article-title":"Entropy-Based Ensemble of Convolutional Neural Networks for Clothes Texture Pattern Recognition","volume":"14","author":"Hasaneen","year":"2022","journal-title":"Appl. Sci."},{"key":"ref_29","unstructured":"Malinin, A., and Gales, M. (2019). Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness. Advances in Neural Information Processing Systems, NeurIPS."},{"key":"ref_30","unstructured":"Sensoy, M., Kaplan, L., and Kandemir, M. (2018, January 3\u20138). Evidential Deep Learning to Quantify Classification Uncertainty. Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.1109\/TAI.2023.3323918","article-title":"Kullback\u2013Leibler Divergence-Based Regularized Normalization for Low-Resource Tasks","volume":"5","author":"Kumar","year":"2023","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_32","unstructured":"Lee, K., Lee, H., Lee, K., and Shin, J. (May, January 30). Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples. Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1016\/j.jksuci.2023.01.014","article-title":"A comprehensive review on ensemble deep learning: Opportunities and challenges","volume":"35","author":"Mohammed","year":"2023","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"13405","DOI":"10.1038\/s41598-025-97561-8","article-title":"Ensemble stacked model for enhanced identification of sentiments from IMDB reviews","volume":"15","author":"Azim","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_35","first-page":"234","article-title":"A hybrid approach for text classification","volume":"10","author":"Kavitha","year":"2023","journal-title":"Int. J. Res. Anal. Rev."},{"key":"ref_36","unstructured":"Ashiga, M., Jie, W., Wu, F., Voskanyan, V., Dinmohammadi, F., Brookes, P., Gong, J., and Wang, Z. (2025). Ensemble learning for large language models in text and code generation. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ibrahim, Y., Okafor, E., Yahaya, B., Yusuf, S.M., Abubakar, Z.M., and Bagaye, U.Y. (2021, January 15\u201316). Comparative study of ensemble learning techniques for text classification. Proceedings of the 2021 1st International Conference on Multidisciplinary Engineering and Applied Science (ICMEAS), Abuja, Nigeria.","DOI":"10.1109\/ICMEAS52683.2021.9692306"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term-weighting approaches in automatic text retrieval","volume":"24","author":"Salton","year":"1988","journal-title":"Inf. Process. Manag."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","article-title":"Distributional structure","volume":"10","author":"Harris","year":"1954","journal-title":"Word"},{"key":"ref_40","unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013, January 2\u20134). Efficient estimation of word representations in vector space. Proceedings of the International Conference on Learning Representations (ICLR), Scottsdale, AZ, USA."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., and Manning, C.D. (2014, January 25\u201329). GloVe: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied Logistic Regression, John Wiley & Sons. [3rd ed.].","DOI":"10.1002\/9781118548387"},{"key":"ref_45","unstructured":"McCallum, A., and Nigam, K. (1998, January 2\u20137). A comparison of event models for Naive Bayes text classification. Proceedings of the AAAI-98 Workshop on Learning for Text Categorization, Bethesda, MD, USA."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf, B., and Smola, A.J. (2002). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press.","DOI":"10.7551\/mitpress\/4175.001.0001"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_50","unstructured":"Tan, F. (2026, February 02). CausalNewsCorpus. GitHub Repository. Available online: https:\/\/github.com\/tanfiona\/CausalNewsCorpus\/tree\/master\/data\/V1."},{"key":"ref_51","first-page":"333","article-title":"CausaLM: Causal Model Explanation through Counterfactual Language Models","volume":"47","author":"Feder","year":"2021","journal-title":"Comput. Linguist."}],"container-title":["Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9709\/13\/3\/37\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T11:24:27Z","timestamp":1772537067000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9709\/13\/3\/37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":51,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["informatics13030037"],"URL":"https:\/\/doi.org\/10.3390\/informatics13030037","relation":{},"ISSN":["2227-9709"],"issn-type":[{"value":"2227-9709","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]}}}