Ensemble-based Methods for Multi-label Classification on Biomedical Question-Answer Data
Background: Question-answer (QA) is a popular method to seek health-related information and biomedical data. Such questions can refer to more than one medical entity (multi-label) so determining the correct tags is not easy. The question classification (QC) mechanism in a QA system can narrow down the answers we are seeking.
Objective: This study develops a multi-label classification using the heterogeneous ensembles method to improve accuracy in biomedical data with long text dimensions.
Methods: We used the ensemble method with heterogeneous deep learning and machine learning for multi-label extended text classification. There are 15 various single models consisting of three deep learning (CNN, LSTM, and BERT) and four machine learning algorithms (SVM, kNN, Decision Tree, and Naïve Bayes) with various text representations (TF-IDF, Word2Vec, and FastText). We used the bagging approach with a hard voting mechanism for the decision-making.
Results: The result shows that deep learning is more powerful than machine learning as a single multi-label biomedical data classification method. Moreover, we found that top-three was the best number of base learners by combining the ensembles method. Heterogeneous-based ensembles with three learners resulted in an F1-score of 82.3%, which is better than the best single model by CNN with an F1-score of 80%.
Conclusion: A multi-label classification of biomedical QA using ensemble models is better than single models. The result shows that heterogeneous ensembles are more potent than homogeneous ensembles on biomedical QA data with long text dimensions.
Keywords: Biomedical Question Classification, Ensemble Method, Heterogeneous Ensembles, Multi-Label Classification, Question Answering
S. Liu, H. Wang, B. Gao, dan Z. Deng, “Doctors’ Provision of Online Health Consultation Service and Patient Review Valence: Evidence from a Quasi-Experiment,” Inf. Manag., no. March 2019, hal. 103360, 2020, doi: 10.1016/j.im.2020.103360.
A. Ben Abacha dan P. Zweigenbaum, “MEANS: A medical question-answering system combining NLP techniques and semantic Web technologies,” Inf. Process. Manag., vol. 51, no. 5, hal. 570–594, 2015, doi: 10.1016/j.ipm.2015.04.006.
E. Dimitrakis, K. Sgontzos, dan Y. Tzitzikas, “A survey on question answering systems over linked data and documents,” J. Intell. Inf. Syst., vol. 55, no. 2, hal. 233–259, 2020, doi: 10.1007/s10844-019-00584-7.
M. A. Calijorne Soares dan F. S. Parreiras, “A literature review on question answering techniques, paradigms and systems,” J. King Saud Univ. - Comput. Inf. Sci., vol. 32, no. 6, hal. 635–646, 2020, doi: 10.1016/j.jksuci.2018.08.005.
M. Zulqarnain, R. Ghazali, M. G. Ghouse, N. A. Husaini, A. K. Z. Alsaedi, dan W. Sharif, “A comparative analysis on question classification task based on deep learning approaches,” PeerJ Comput. Sci., vol. 7, hal. 1–27, 2021, doi: 10.7717/PEERJ-CS.570.
N. Chen, X. Su, T. Liu, Q. Hao, dan M. Wei, “A benchmark dataset and case study for Chinese medical question intent classification,” BMC Med. Inform. Decis. Mak., vol. 20, no. Suppl 3, hal. 1–7, 2020, doi: 10.1186/s12911-020-1122-3.
M. Wasim, M. N. Asim, M. U. Ghani Khan, dan W. Mahmood, “Multi-label biomedical question classification for lexical answer type prediction,” J. Biomed. Inform., vol. 93, no. March, hal. 103143, 2019, doi: 10.1016/j.jbi.2019.103143.
M. P. Sesmero, J. A. Iglesias, E. Magán, A. Ledezma, dan A. Sanchis, “Impact of the learners diversity and combination method on the generation of heterogeneous classifier ensembles,” Appl. Soft Comput., vol. 111, hal. 107689, 2021, doi: 10.1016/j.asoc.2021.107689.
J. Kazmaier dan J. H. van Vuuren, “The power of ensemble learning in sentiment analysis,” Expert Syst. Appl., vol. 187, no. June 2021, 2022, doi: 10.1016/j.eswa.2021.115819.
G. Chen, D. Ye, Z. Xing, J. Chen, dan E. Cambria, “Ensemble application of convolutional and recurrent neural networks for multi-label text categorization,” Proc. Int. Jt. Conf. Neural Networks, vol. 2017-May, hal. 2377–2383, 2017, doi: 10.1109/IJCNN.2017.7966144.
A. Onan, S. Korukoǧlu, dan H. Bulut, “Ensemble of keyword extraction methods and classifiers in text classification,” Expert Syst. Appl., vol. 57, hal. 232–247, 2016, doi: 10.1016/j.eswa.2016.03.045.
A. Onan, “An ensemble scheme based on language function analysis and feature engineering for text genre classification,” J. Inf. Sci., vol. 44, no. 1, hal. 28–47, 2018, doi: 10.1177/0165551516677911.
H. Liu, G. Chen, P. Li, P. Zhao, dan X. Wu, “Multi-label text classification via joint learning from label embedding and label correlation,” Neurocomputing, vol. 460, hal. 385–398, 2021, doi: 10.1016/j.neucom.2021.07.031.
M. A. Ibrahim, M. U. Ghani Khan, F. Mehmood, M. N. Asim, dan W. Mahmood, “GHS-NET a generic hybridized shallow neural network for multi-label biomedical text classification,” J. Biomed. Inform., vol. 116, no. November 2020, hal. 103699, 2021, doi: 10.1016/j.jbi.2021.103699.
A. Onan, “Classifier and feature set ensembles for web page classification,” J. Inf. Sci., vol. 42, no. 2, hal. 150–165, 2016, doi: 10.1177/0165551515591724.
Y. Xia, K. Chen, dan Y. Yang, “Multi-label classification with weighted classifier selection and stacked ensemble,” Inf. Sci. (Ny)., vol. 557, hal. 421–442, 2021, doi: 10.1016/j.ins.2020.06.017.
J. Noh dan R. Kavuluru, “Improved biomedical word embeddings in the transformer era,” J. Biomed. Inform., vol. 120, hal. 103867, Agu 2021, doi: 10.1016/j.jbi.2021.103867.
M. Mohammedid dan N. Omar, “Question classification based on Bloom’s taxonomy cognitive domain using modified TF-IDF and word2vec,” PLoS One, vol. 15, no. 3, hal. 1–21, 2020, doi: 10.1371/journal.pone.0230442.
K. Pliakos dan C. Vens, “Mining features for biomedical data using clustering tree ensembles,” J. Biomed. Inform., vol. 85, hal. 40–48, Sep 2018, doi: 10.1016/j.jbi.2018.07.012.
Z. Shaheen, G. Wohlgenannt, dan E. Filtz, “Large Scale Legal Text Classification Using Transformer Models,” Okt 2020, [Daring]. Tersedia pada: http://arxiv.org/abs/2010.12871.
R. Wang, R. Ridley, X. Su, W. Qu, dan X. Dai, “A novel reasoning mechanism for multi-label text classification,” Inf. Process. Manag., vol. 58, no. 2, hal. 102441, Mar 2021, doi: 10.1016/j.ipm.2020.102441.
V. L. Nguyen, E. Hüllermeier, M. Rapp, E. Loza Mencía, dan J. Fürnkranz, “On Aggregation in Ensembles of Multilabel Classifiers,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12323 LNAI, hal. 533–547, 2020, doi: 10.1007/978-3-030-61527-7_35.
M. Izadi, A. Heydarnoori, dan G. Gousios, “Topic recommendation for software repositories using multi-label classification algorithms,” Empir. Softw. Eng., vol. 26, no. 5, hal. 1–33, 2021, doi: 10.1007/s10664-021-09976-2.
F. Zhou et al., “Online Clinical Consultation as a Utility Tool for Managing Medical Crisis During a Pandemic: Retrospective Analysis on the Characteristics of Online Clinical Consultations During the COVID-19 Pandemic,” J. Prim. Care Community Heal., vol. 11, 2020, doi: 10.1177/2150132720975517.
M. A. Ganaie, M. Hu, M. Tanveer*, dan P. N. Suganthan*, “Ensemble deep learning: A review,” 2021, [Daring]. Tersedia pada: http://arxiv.org/abs/2104.02395.
Z. Sun, C. Wang, Y. Zhao, dan C. Yan, “Multi-Label ECG Signal Classification Based on Ensemble Classifier,” IEEE Access, vol. 8, hal. 117986–117996, 2020, doi: 10.1109/ACCESS.2020.3004908.
Copyright (c) 2022 The Authors. Published by Universitas Airlangga.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
All accepted papers will be published under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. Authors retain copyright and grant the journal right of first publication. CC-BY Licenced means lets others to Share (copy and redistribute the material in any medium or format) and Adapt (remix, transform, and build upon the material for any purpose, even commercially).