{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:03:49Z","timestamp":1781006629147,"version":"3.54.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2028,5,4]],"date-time":"2028-05-04T00:00:00Z","timestamp":1841011200000},"content-version":"am","delay-in-days":703,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116047","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:08:18Z","timestamp":1777306098000},"page":"116047","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["IBIS-Net: An iterative bio-inspired selection network for interpretable text classification"],"prefix":"10.1016","volume":"345","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9907-6538","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7379-1374","authenticated-orcid":false,"given":"Yuki","family":"Todo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116047_b1","doi-asserted-by":"crossref","unstructured":"Y. Kim, Convolutional Neural Networks for Sentence Classification, in: Proceedings of EMNLP, 2014, pp. 1746\u20131751.","DOI":"10.3115\/v1\/D14-1181"},{"key":"10.1016\/j.knosys.2026.116047_b2","doi-asserted-by":"crossref","unstructured":"Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, E. Hovy, Hierarchical Attention Networks for Document Classification, in: Proceedings of NAACL-HLT, 2016, pp. 1480\u20131489.","DOI":"10.18653\/v1\/N16-1174"},{"key":"10.1016\/j.knosys.2026.116047_b3","series-title":"Advances in Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.knosys.2026.116047_b4","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in: Proceedings NAACL-HLT, 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.knosys.2026.116047_b5","series-title":"RoBERTa: A robustly optimized BERT pretraining approach","first-page":"1","author":"Liu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116047_b6","unstructured":"P. He, X. Liu, J. Gao, W. Chen, DeBERTa: Decoding-Enhanced BERT with Disentangled Attention, in: Proceedings of the International Conference on Learning Representations, 2021, pp. 1\u2013."},{"key":"10.1016\/j.knosys.2026.116047_b7","series-title":"ERNIE: Enhanced representation through knowledge integration","author":"Sun","year":"2019"},{"issue":"140","key":"10.1016\/j.knosys.2026.116047_b8","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116047_b9","unstructured":"I. Beltagy, M.E. Peters, A. Cohan, Longformer: The Long-Document Transformer, in: Proceedings of ACL, 2020, pp. 1\u201315."},{"issue":"2","key":"10.1016\/j.knosys.2026.116047_b10","first-page":"1","article-title":"Long document classification in the transformer era: A survey on challenges, advances, and open issues","volume":"15","author":"Alva Principe","year":"2025","journal-title":"WIREs Data Min. Knowl. Discov."},{"key":"10.1016\/j.knosys.2026.116047_b11","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"6559","article-title":"Efficient classification of long documents via state-space models","author":"Lu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116047_b12","series-title":"Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)","first-page":"278","article-title":"Length-aware multi-kernel transformer for long document classification","author":"Han","year":"2024"},{"key":"10.1016\/j.knosys.2026.116047_b13","unstructured":"Z. Lin, M. Feng, C.N. dos Santos, M. Yu, B. Xiang, B. Zhou, Y. Bengio, A Structured Self-Attentive Sentence Embedding, in: Proceedings of the International Conference on Learning Representations, 2017, pp. 1\u2013."},{"key":"10.1016\/j.knosys.2026.116047_b14","doi-asserted-by":"crossref","unstructured":"Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, E. Hovy, Hierarchical Attention Networks for Document Classification, in: Proceedings of NAACL-HLT, 2016, pp. 1480\u20131489.","DOI":"10.18653\/v1\/N16-1174"},{"issue":"1","key":"10.1016\/j.knosys.2026.116047_b15","first-page":"7370","article-title":"Graph convolutional networks for text classification","volume":"33","author":"Yao","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116047_b16","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"SpanBERT: Improving pre-training by representing and predicting spans","volume":"8","author":"Joshi","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.116047_b17","doi-asserted-by":"crossref","unstructured":"M.T. Ribeiro, S. Singh, C. Guestrin, \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier, in: Proceedings of KDD, 2016, pp. 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"issue":"12","key":"10.1016\/j.knosys.2026.116047_b18","doi-asserted-by":"crossref","first-page":"360","DOI":"10.3390\/languages9120360","article-title":"Tracking adults\u2019 eye movements to study text comprehension: A review article","volume":"9","author":"Andreou","year":"2024","journal-title":"Languages"},{"issue":"1","key":"10.1016\/j.knosys.2026.116047_b19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3758\/PBR.16.1.1","article-title":"Using E-Z reader to model the effects of higher level language processing on eye movements during reading","volume":"16","author":"Reichle","year":"2009","journal-title":"Psychon. Bull. Rev."},{"key":"10.1016\/j.knosys.2026.116047_b20","doi-asserted-by":"crossref","unstructured":"T. Lei, R. Barzilay, T. Jaakkola, Rationalizing Neural Predictions, in: Proceedings of EMNLP, 2016, pp. 107\u2013117.","DOI":"10.18653\/v1\/D16-1011"},{"key":"10.1016\/j.knosys.2026.116047_b21","series-title":"Proceedings NAACL-HLT","first-page":"11","article-title":"Attention is not explanation","volume":"vol. 1","author":"Wiegreffe","year":"2019"},{"key":"10.1016\/j.knosys.2026.116047_b22","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"SpanBERT: Improving pre-training by representing and predicting spans","volume":"8","author":"Joshi","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.116047_b23","series-title":"Advances in Neural Information Processing Systems","first-page":"305","article-title":"Learning where to attend with deep architectures for document classification","author":"Denil","year":"2014"},{"key":"10.1016\/j.knosys.2026.116047_b24","doi-asserted-by":"crossref","unstructured":"J. Li, M.-T. Luong, D. Jurafsky, Hierarchical Neural Autoencoders for Paragraphs and Documents, in: Proceedings of ACL, 2015, pp. 1106\u20131115.","DOI":"10.3115\/v1\/P15-1107"},{"key":"10.1016\/j.knosys.2026.116047_b25","unstructured":"Y. Yang, A. Nenkova, Hierarchical Attention with Memory for Document Classification, in: Proceedings of NAACL-HLT, 2016, pp. 556\u2013566."},{"key":"10.1016\/j.knosys.2026.116047_b26","doi-asserted-by":"crossref","unstructured":"J. Cheng, L. Dong, M. Lapata, Long Short-Term Memory-Networks for Machine Reading, in: Proceedings of EMNLP, 2016, pp. 551\u2013561.","DOI":"10.18653\/v1\/D16-1053"},{"key":"10.1016\/j.knosys.2026.116047_b27","unstructured":"Y. Ji, N.A. Smith, Discourse Relations for Document-Level Sentiment Classification, in: Proceedings of ACL, 2014, pp. 1556\u20131566."},{"key":"10.1016\/j.knosys.2026.116047_b28","doi-asserted-by":"crossref","unstructured":"J. Li, D. Jurafsky, A Hierarchical Neural Autoencoder for Paragraph and Document Modeling, in: Proceedings of ACL, 2016, pp. 1106\u20131115.","DOI":"10.3115\/v1\/P15-1107"},{"key":"10.1016\/j.knosys.2026.116047_b29","unstructured":"B. Huang, K.M. Carley, Text Classification with Heterogeneous Graph Attention Network, in: Proceedings EMNLP-IJCNLP, 2019, pp. 4546\u20134555."},{"key":"10.1016\/j.knosys.2026.116047_b30","first-page":"112859","article-title":"Text classification of coronavirus-related tweets using graph neural networks","volume":"8","author":"Luo","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2026.116047_b31","doi-asserted-by":"crossref","unstructured":"S. Narayan, S.B. Cohen, M. Lapata, Ranking Sentences for Extractive Summarization with Reinforcement Learning, in: Proceedings of NAACL-HLT, 2018, pp. 1747\u20131759.","DOI":"10.18653\/v1\/N18-1158"},{"key":"10.1016\/j.knosys.2026.116047_b32","unstructured":"Q. Zhou, N. Yang, F. Wei, C. Tan, M. Zhou, Hierarchical Reinforcement Learning for Extractive Summarization, in: Proceedings of ACL, 2019, pp. 1795\u20131805."},{"key":"10.1016\/j.knosys.2026.116047_b33","unstructured":"R. Reichart, R. Barzilay, Text Understanding from Scratch, in: Proceedings of ACL, 2012, pp. 246\u2013255."},{"key":"10.1016\/j.knosys.2026.116047_b34","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116047_b35","unstructured":"O. Zaidan, J. Eisner, C. Piatko, Using Annotator Rationales to Improve Machine Learning for Text Categorization, in: Proceedings of NAACL-HLT, 2007, pp. 260\u2013267."},{"key":"10.1016\/j.knosys.2026.116047_b36","doi-asserted-by":"crossref","unstructured":"Y. Zhang, I.J. Marshall, B.C. Wallace, Rationale-Augmented Convolutional Neural Networks for Text Classification, in: Proceedings of EMNLP, 2016, pp. 795\u2013804.","DOI":"10.18653\/v1\/D16-1076"},{"key":"10.1016\/j.knosys.2026.116047_b37","unstructured":"D. Alvarez-Melis, T. Jaakkola, Towards Interpretable Natural Language Processing, in: Proceedings of NAACL-HLT, 2018, pp. 184\u2013194."},{"key":"10.1016\/j.knosys.2026.116047_b38","first-page":"121","article-title":"Bridging the gap between human and neural explanations","volume":"9","author":"Rao","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.116047_b39","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2024.1363531","article-title":"From outputs to insights: A survey of rationalization approaches for explainable text classification","volume":"7","author":"Mendez Guzman","year":"2024","journal-title":"Front. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116047_b40","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2024.1260952","article-title":"Human-annotated rationales and explainable text classification: A survey","volume":"7","author":"Herrewijnen","year":"2024","journal-title":"Front. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116047_b41","unstructured":"A. Jacovi, Y. Goldberg, Towards Faithfully Interpretable NLP Systems, in: Proceedings of ACL, 2020, pp. 4197\u20134205."},{"key":"10.1016\/j.knosys.2026.116047_b42","first-page":"129","article-title":"Locating and understanding neuron-level explanations in neural language models","volume":"10","author":"Liao","year":"2022","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.116047_b43","series-title":"Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)","first-page":"409","article-title":"Connecting concept layers and rationales to enhance language model interpretability","author":"Bailleux","year":"2025"},{"key":"10.1016\/j.knosys.2026.116047_b44","series-title":"Advances in Neural Information Processing Systems","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"Zhang","year":"2015"},{"key":"10.1016\/j.knosys.2026.116047_b45","unstructured":"A.L. Maas, R.E. Daly, P.T. Pham, D. Huang, A.Y. Ng, C. Potts, Learning Word Vectors for Sentiment Analysis, in: Proceedings of ACL-HLT, 2011, pp. 142\u2013150."},{"key":"10.1016\/j.knosys.2026.116047_b46","doi-asserted-by":"crossref","unstructured":"J. McAuley, R. Pandey, J. Leskovec, Image-based Recommendations on Styles and Substitutes, in: Proceedings of SIGIR, 2015, pp. 43\u201352.","DOI":"10.1145\/2766462.2767755"},{"key":"10.1016\/j.knosys.2026.116047_b47","series-title":"NeurIPS Workshop on Energy Efficient Machine Learning and Cognitive Computing","first-page":"1","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"10.1016\/j.knosys.2026.116047_b48","unstructured":"Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, R. Soricut, ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations, in: Proceedings of the International Conference on Learning Representations, 2020, pp. 1\u2013."},{"key":"10.1016\/j.knosys.2026.116047_b49","doi-asserted-by":"crossref","unstructured":"A. Conneau, G. Lample, M. Ranzato, L. Denoyer, H. J\u00e9gou, Unsupervised Cross-lingual Representation Learning at Scale, in: Proceedings of ACL, 2020, pp. 8440\u20138451.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"10.1016\/j.knosys.2026.116047_b50","unstructured":"K. Clark, M.-T. Luong, Q. Le, C.D. Manning, ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators, in: Proceedings of the International Conference on Learning Representations, 2020, pp. 1\u2013."},{"key":"10.1016\/j.knosys.2026.116047_b51","series-title":"Advances in Neural Information Processing Systems","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","author":"Zaheer","year":"2020"},{"key":"10.1016\/j.knosys.2026.116047_b52","series-title":"Proceedings of the 13th International Workshop on Semantic Evaluation","first-page":"829","article-title":"SemEval-2019 task 4: Hyperpartisan news detection","author":"Kiesel","year":"2019"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007732?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007732?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:32:27Z","timestamp":1781004747000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126007732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":52,"alternative-id":["S0950705126007732"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116047","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"IBIS-Net: An iterative bio-inspired selection network for interpretable text classification","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116047","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116047"}}