{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T04:28:45Z","timestamp":1741753725354,"version":"3.38.0"},"reference-count":53,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2024,9,19]]},"abstract":"<jats:p>Active Learning (AL) is a technique being widely employed to minimize the time and labor costs in the task of annotating data. By querying and extracting the specific instances to train the model, the relevant task\u2019s performance is improved maximally within limited iterations. However, rare work was conducted to fully fuse features from different hierarchies to enhance the effectiveness of active learning. Inspired by the thought of information compensation in many famous deep learning models (such as ResNet, etc.), this work proposes a novel TextCNN-based Two ways Active Learning model (TCTWAL) to extract task-relevant texts. TextCNN takes the advantage of little hyper-parameter tuning and static vectors and achieves excellent results on various natural language processing (NLP) tasks, which are also beneficial to human-computer interaction (HCI) and the AL relevant tasks. In the process of the proposed AL model, the candidate texts are measured from both global and local features by the proposed AL framework TCTWAL depending on the modified TextCNN. Besides, the query strategy is strongly enhanced by maximum normalized log-probability (MNLP), which is sensitive to detecting the longer sentences. Additionally, the selected instances are characterized by general global information and abundant local features simultaneously. To validate the effectiveness of the proposed model, extensive experiments are conducted on three widely used text corpus, and the results are compared with with eight manual designed instance query strategies. The results show that our method outperforms the planned baselines in terms of accuracy, macro precision, macro recall, and macro F1 score. Especially, to the classification results on AG\u2019s News corpus, the improvements of the four indicators after 39 iterations are 40.50%, 45.25%, 48.91%, and 45.25%, respectively.<\/jats:p>","DOI":"10.3233\/ida-230332","type":"journal-article","created":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T16:29:26Z","timestamp":1708705766000},"page":"1189-1211","source":"Crossref","is-referenced-by-count":0,"title":["A dual-ways feature fusion mechanism enhancing active learning based on TextCNN"],"prefix":"10.1177","volume":"28","author":[{"given":"Xuefeng","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology, Anhui, China"}]},{"given":"Min","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology, Anhui, China"}]},{"given":"Fuji","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Sichuan, China"}]},{"given":"Piao","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer and Information, Hefei University of Technology, Anhui, China"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-230332_ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3034215"},{"issue":"4","key":"10.3233\/IDA-230332_ref2","doi-asserted-by":"crossref","first-page":"e0194136","DOI":"10.1371\/journal.pone.0194136","article-title":"Emotion computing using Word Mover\u00e2\u0080\u0099s Distance features based on Ren_CECps","volume":"13","author":"Ren","year":"2018","journal-title":"PloS One"},{"key":"10.3233\/IDA-230332_ref3","doi-asserted-by":"crossref","unstructured":"A. Parvaneh, E. Abbasnejad, D. Teney, R. Haffari, A. van den Hengel and J.Q. Shi, Active Learning by Feature Mixing, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 12227\u201312236. https:\/\/api.semanticscholar.org\/CorpusID:247446741.","DOI":"10.1109\/CVPR52688.2022.01192"},{"issue":"4","key":"10.3233\/IDA-230332_ref4","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1007\/s11390-020-9487-4","article-title":"Active learning query strategies for classification, regression, and clustering: A survey","volume":"35","author":"Kumar","year":"2020","journal-title":"Journal of Computer Science and Technology"},{"issue":"3","key":"10.3233\/IDA-230332_ref5","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1007\/s13042-021-01356-y","article-title":"Emotion-enhanced classification based on fuzzy reasoning","volume":"13","author":"Yan","year":"2022","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"4","key":"10.3233\/IDA-230332_ref6","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1049\/cje.2021.05.007","article-title":"Keyword Extraction from Scientific Research Projects Based on SRP-TF-IDF","volume":"30","author":"Zhuohao","year":"2021","journal-title":"Chinese Journal of Electronics"},{"key":"10.3233\/IDA-230332_ref7","doi-asserted-by":"crossref","first-page":"18073","DOI":"10.1007\/s00521-023-08597-8","article-title":"Testing machine learning explanation methods","volume":"35","author":"Anderson","year":"2023","journal-title":"Neural Computing and Applications"},{"key":"10.3233\/IDA-230332_ref8","doi-asserted-by":"crossref","unstructured":"V. Prabhu, A. Chandrasekaran, K. Saenko and J. Hoffman, Active domain adaptation via clustering uncertainty-weighted embeddings, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp.\u00a08505\u20138514.","DOI":"10.1109\/ICCV48922.2021.00839"},{"key":"10.3233\/IDA-230332_ref9","doi-asserted-by":"crossref","unstructured":"J. Wu, J. Chen and D. Huang, Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 9387\u20139396. https:\/\/api.semanticscholar.org\/CorpusID:248227933.","DOI":"10.1109\/CVPR52688.2022.00918"},{"issue":"20","key":"10.3233\/IDA-230332_ref10","doi-asserted-by":"crossref","first-page":"8314","DOI":"10.3390\/su12208314","article-title":"The application of fuzzy Analytic Hierarchy Process in sustainable project selection","volume":"12","author":"Alyamani","year":"2020","journal-title":"Sustainability"},{"key":"10.3233\/IDA-230332_ref11","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a0770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"10.3233\/IDA-230332_ref13","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.32604\/cmc.2020.09962","article-title":"MII: A novel text classification model combining deep active learning with bert","volume":"63","author":"Zhang","year":"2020","journal-title":"Computers Materials and Continua"},{"key":"10.3233\/IDA-230332_ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2020.2986875","article-title":"Autolabeling-enhanced active learning for cost-efficient surface defect visual classification","volume":"70","author":"Yang","year":"2020","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.3233\/IDA-230332_ref15","unstructured":"C. Shui, F. Zhou, C. Gagn\u00e9 and B. Wang, Deep active learning: Unified and principled method for query and training, in: International Conference on Artificial Intelligence and Statistics, PMLR, 2020, pp.\u00a01308\u20131318."},{"issue":"19","key":"10.3233\/IDA-230332_ref16","doi-asserted-by":"crossref","first-page":"12535","DOI":"10.1007\/s00521-021-05896-w","article-title":"NE-LP: Normalized entropy-and loss prediction-based sampling for active learning in Chinese word segmentation on EHRs","volume":"33","author":"Cai","year":"2021","journal-title":"Neural Computing and Applications"},{"key":"10.3233\/IDA-230332_ref17","doi-asserted-by":"crossref","unstructured":"D.D. Lewis and W.A. Gale, A sequential algorithm for training text classifiers, in: SIGIR\u00e2\u0080\u009994, Springer, 1994, pp.\u00a03\u201312.","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"10.3233\/IDA-230332_ref18","doi-asserted-by":"crossref","unstructured":"T. Scheffer, C. Decomain and S. Wrobel, Active hidden markov models for information extraction, in: International Symposium on Intelligent Data Analysis, Springer, 2001, pp.\u00a0309\u2013318.","DOI":"10.1007\/3-540-44816-0_31"},{"issue":"4","key":"10.3233\/IDA-230332_ref19","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1017\/pan.2020.4","article-title":"Active learning approaches for labeling text: Review and assessment of the performance of active learning approaches","volume":"28","author":"Miller","year":"2020","journal-title":"Political Analysis"},{"issue":"12","key":"10.3233\/IDA-230332_ref20","doi-asserted-by":"crossref","first-page":"9524","DOI":"10.1109\/TGRS.2019.2927393","article-title":"Half a percent of labels is enough: Efficient animal detection in UAV imagery using deep CNNs and active learning","volume":"57","author":"Kellenberger","year":"2019","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.3233\/IDA-230332_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3038401"},{"key":"10.3233\/IDA-230332_ref22","doi-asserted-by":"crossref","unstructured":"X. Kang, Y. Wu and F. Ren, Progressively improving supervised emotion classification through active learning, in: International Conference on Multi-disciplinary Trends in Artificial Intelligence, Springer, 2018, pp.\u00a049\u201357.","DOI":"10.1007\/978-3-030-03014-8_4"},{"key":"10.3233\/IDA-230332_ref23","doi-asserted-by":"crossref","unstructured":"Y. Siddiqui, J. Valentin and M. Nie\u00dfner, Viewal: Active learning with viewpoint entropy for semantic segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a09433\u20139443.","DOI":"10.1109\/CVPR42600.2020.00945"},{"key":"10.3233\/IDA-230332_ref24","doi-asserted-by":"crossref","first-page":"471","DOI":"10.3389\/fpsyg.2021.642347","article-title":"Attention-based deep entropy active learning using lexical algorithm for mental health treatment","volume":"12","author":"Ahmed","year":"2021","journal-title":"Frontiers in Psychology"},{"key":"10.3233\/IDA-230332_ref26","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.ins.2018.05.014","article-title":"Query-by-committee improvement with diversity and density in batch active learning","volume":"454","author":"Kee","year":"2018","journal-title":"Information Sciences"},{"key":"10.3233\/IDA-230332_ref27","doi-asserted-by":"crossref","first-page":"297","DOI":"10.3390\/rs14020297","article-title":"DBSCAN and TD Integrated Wi-Fi Positioning Algorithm","volume":"14","author":"Bi","year":"2022","journal-title":"Remote Sensing"},{"key":"10.3233\/IDA-230332_ref28","doi-asserted-by":"crossref","unstructured":"Y. Yang and C. Zhang, Attention-Based Multi-level Network for Text Matching with Feature Fusion, in: 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence, 2021, pp.\u00a01\u20137.","DOI":"10.1145\/3508546.3508632"},{"key":"10.3233\/IDA-230332_ref29","doi-asserted-by":"crossref","unstructured":"P. Shayegh, Y. Li, J. Zhang and Q. Zhang, Semi-supervised text classification with deep convolutional neural network using feature fusion approach, in: 2019 IEEE\/WIC\/ACM International Conference on Web Intelligence (WI), IEEE, 2019, pp.\u00a0363\u2013366.","DOI":"10.1145\/3350546.3352548"},{"issue":"12","key":"10.3233\/IDA-230332_ref30","doi-asserted-by":"crossref","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","article-title":"Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering","volume":"29","author":"Yu","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"3","key":"10.3233\/IDA-230332_ref31","doi-asserted-by":"crossref","first-page":"1542","DOI":"10.1109\/TCYB.2019.2939399","article-title":"Multimodal fusion for objective assessment of cognitive workload: A review","volume":"51","author":"Debie","year":"2019","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"4","key":"10.3233\/IDA-230332_ref32","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1016\/j.ipm.2019.02.018","article-title":"Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion","volume":"56","author":"Abdi","year":"2019","journal-title":"Information Processing & Management"},{"key":"10.3233\/IDA-230332_ref33","doi-asserted-by":"crossref","unstructured":"S. Zhang, X. Lv, Y. Tang and Z. Dong, Movie short-text reviews sentiment analysis based on multi-feature fusion, in: Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence, 2018, pp.\u00a01\u20136.","DOI":"10.1145\/3302425.3302469"},{"key":"10.3233\/IDA-230332_ref34","first-page":"27","article-title":"Learning the kernel matrix with semidefinite programming","volume":"5","author":"Lanckriet","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-230332_ref35","unstructured":"M. Kloft and G. Blanchard, The local rademacher complexity of lp-norm multiple kernel learning, Advances in Neural Information Processing Systems 24 (2011)."},{"key":"10.3233\/IDA-230332_ref36","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TFUZZ.2020.3041588","article-title":"Fuzzy-model-based control for singularly perturbed systems with nonhomogeneous markov switching: A dropout compensation strategy","volume":"30","author":"Cheng","year":"2022","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"10.3233\/IDA-230332_ref37","unstructured":"C. Duan, J. Ding, S. Chen, Z. Yu and T. Huang, Temporal Effective Batch Normalization in Spiking Neural Networks, in: Neural Information Processing Systems, 2022. https:\/\/api.semanticscholar.org\/CorpusID:258509732."},{"key":"10.3233\/IDA-230332_ref38","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/j.neucom.2019.07.052","article-title":"Improving text classification with weighted word embeddings via a multi-channel TextCNN model","volume":"363","author":"Guo","year":"2019","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-230332_ref39","doi-asserted-by":"crossref","first-page":"103957","DOI":"10.1016\/j.jbi.2021.103957","article-title":"Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types","volume":"125","author":"De\u00a0Angeli","year":"2022","journal-title":"Journal of Biomedical Informatics"},{"issue":"7","key":"10.3233\/IDA-230332_ref41","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.3390\/diagnostics11071212","article-title":"Dilated semantic segmentation for breast ultrasonic lesion detection using parallel feature fusion","volume":"11","author":"Irfan","year":"2021","journal-title":"Diagnostics"},{"issue":"4","key":"10.3233\/IDA-230332_ref42","doi-asserted-by":"crossref","first-page":"820","DOI":"10.3390\/math11040820","article-title":"A survey on active learning: State-of-the-art, practical challenges and research directions","volume":"11","author":"Tharwat","year":"2023","journal-title":"Mathematics"},{"key":"10.3233\/IDA-230332_ref43","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1109\/MITS.2022.3174238","article-title":"The fault diagnosis of a switch machine based on deep random forest fusion","volume":"15","author":"Cao","year":"2023","journal-title":"IEEE Intelligent Transportation Systems Magazine"},{"key":"10.3233\/IDA-230332_ref44","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1109\/TIV.2022.3161301","article-title":"Real-time state of charge estimation of lithium-ion batteries using optimized random forest regression algorithm","volume":"8","author":"Lipu","year":"2023","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"issue":"3","key":"10.3233\/IDA-230332_ref45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3178582","article-title":"A survey of random forest based methods for intrusion detection systems","volume":"51","author":"Resende","year":"2018","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.3233\/IDA-230332_ref46","doi-asserted-by":"crossref","first-page":"e5518","DOI":"10.7717\/peerj.5518","article-title":"Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables","volume":"6","author":"Hengl","year":"2018","journal-title":"PeerJ"},{"key":"10.3233\/IDA-230332_ref48","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/TAFFC.2020.3031300","article-title":"Ordinal logistic regression with partial proportional odds for depression prediction","volume":"14","author":"Jayawardena","year":"2023","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.3233\/IDA-230332_ref49","doi-asserted-by":"crossref","unstructured":"T.T. Wu, Y. Wei, J. Wu, B. Yi and H. Li, Logistic regression technique is comparable to complex machine learning algorithms in predicting cognitive impairment related to post intensive care syndrome, Scientific Reports 13 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256765500.","DOI":"10.1038\/s41598-023-28421-6"},{"issue":"6","key":"10.3233\/IDA-230332_ref51","doi-asserted-by":"crossref","first-page":"332","DOI":"10.3390\/info11060332","article-title":"Evaluation of tree-based ensemble machine learning models in predicting stock price direction of movement","volume":"11","author":"Ampomah","year":"2020","journal-title":"Information"},{"issue":"10","key":"10.3233\/IDA-230332_ref52","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1109\/LGRS.2019.2953778","article-title":"Land cover classification using extremely randomized trees: A kernel perspective","volume":"17","author":"Zafari","year":"2019","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.3233\/IDA-230332_ref53","doi-asserted-by":"crossref","first-page":"142532","DOI":"10.1109\/ACCESS.2020.3013699","article-title":"Ai meta-learners and extra-trees algorithm for the detection of phishing websites","volume":"8","author":"Alsariera","year":"2020","journal-title":"IEEE Access"},{"issue":"12","key":"10.3233\/IDA-230332_ref54","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1007\/s13042-019-00942-5","article-title":"Word-character attention model for Chinese text classification","volume":"10","author":"Qiao","year":"2019","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"10.3233\/IDA-230332_ref55","doi-asserted-by":"crossref","unstructured":"H. Zhuang, C. Wang, C. Li, Q. Wang and X. Zhou, Natural language processing service based on stroke-level convolutional networks for Chinese text classification, in: 2017 IEEE International Conference on Web Services (ICWS), IEEE, 2017, pp.\u00a0404\u2013411.","DOI":"10.1109\/ICWS.2017.46"},{"issue":"12","key":"10.3233\/IDA-230332_ref56","first-page":"2009","article-title":"Twitter sentiment classification using distant supervision","volume":"1","author":"Go","year":"2009","journal-title":"CS224N project report, Stanford"},{"key":"10.3233\/IDA-230332_ref57","doi-asserted-by":"crossref","unstructured":"H. Pham and Q. Le, Autodropout: Learning dropout patterns to regularize deep networks, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a035, 2021, pp.\u00a09351\u20139359.","DOI":"10.1609\/aaai.v35i11.17127"},{"issue":"11","key":"10.3233\/IDA-230332_ref58","doi-asserted-by":"crossref","first-page":"113","DOI":"10.3390\/fi10110113","article-title":"Chinese text classification model based on deep learning","volume":"10","author":"Li","year":"2018","journal-title":"Future Internet"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-230332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T09:09:10Z","timestamp":1741684150000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospress&doi=10.3233\/IDA-230332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,19]]},"references-count":53,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/ida-230332","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"type":"print","value":"1088-467X"},{"type":"electronic","value":"1571-4128"}],"subject":[],"published":{"date-parts":[[2024,9,19]]}}}