{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:48:55Z","timestamp":1750164535469,"version":"3.37.3"},"reference-count":41,"publisher":"Wiley","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2019207118","ZD2021319","ZD2021043","2019PY01","2020YB13"],"award-info":[{"award-number":["F2019207118","ZD2021319","ZD2021043","2019PY01","2020YB13"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003482","name":"Department of Education of Hebei Province","doi-asserted-by":"publisher","award":["F2019207118","ZD2021319","ZD2021043","2019PY01","2020YB13"],"award-info":[{"award-number":["F2019207118","ZD2021319","ZD2021043","2019PY01","2020YB13"]}],"id":[{"id":"10.13039\/501100003482","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008047","name":"Hebei University","doi-asserted-by":"publisher","award":["F2019207118","ZD2021319","ZD2021043","2019PY01","2020YB13"],"award-info":[{"award-number":["F2019207118","ZD2021319","ZD2021043","2019PY01","2020YB13"]}],"id":[{"id":"10.13039\/501100008047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Quantum Engineering"],"published-print":{"date-parts":[[2023,11,13]]},"abstract":"<jats:p>Very recently, the BERT graph convolutional network (BertGCN) model has attracted much attention from researchers due to its good text classification performance. However, just using original documents in the corpus to construct the topology of graphs for GCN-based models may lose some effective information. In this paper, we focus on sentiment classification, an important branch of text classification, and propose the multistream BERT graph convolutional network (MS-BertGCN) for sentiment classification based on cross-document learning. In the proposed method, we first combine the documents in the training set based on within-class similarity. Then, each heterogeneous graph is constructed using a group of combinations of documents for the single-stream BertGCN model. Finally, we construct multistream-BertGCN (MS-BertGCN) based on multiple heterogeneous graphs constructed from different groups of combined documents. The experimental results show that our MS-BertGCN model outperforms state-of-the-art methods on sentiment classification tasks.<\/jats:p>","DOI":"10.1155\/2023\/3668960","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T17:35:07Z","timestamp":1699896907000},"page":"1-9","source":"Crossref","is-referenced-by-count":2,"title":["Multistream BertGCN for Sentiment Classification Based on Cross-Document Learning"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3497-4391","authenticated-orcid":true,"given":"Meng","family":"Li","sequence":"first","affiliation":[{"name":"College of Mathematics and Statistic, Hebei University of Economics and Business, Shijiazhuang 050062, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9527-1422","authenticated-orcid":true,"given":"Yujin","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Mathematics and Statistic, Hebei University of Economics and Business, Shijiazhuang 050062, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6061-3915","authenticated-orcid":true,"given":"Weifeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang 311121, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0462-6727","authenticated-orcid":true,"given":"Shenyu","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Mathematics and Statistic, Hebei University of Economics and Business, Shijiazhuang 050062, China"}]}],"member":"311","reference":[{"key":"1","first-page":"142","article-title":"Opinion mining and sentiment analysis","volume":"10","author":"R. K. Bakshi","year":"2008","journal-title":"Journal Abbreviation"},{"author":"B. O\u2019Connor","first-page":"559","article-title":"From tweets to polls: linking text sentiment to public opinion time series","key":"2"},{"author":"Y. Zhang","first-page":"435","article-title":"Incorporating phrase-level sentiment analysis on textual reviews for personalized recommendation","key":"3"},{"author":"A. B. Goldberg","first-page":"45","article-title":"Seeing stars when there aren\u2019t many stars: graph-based semi-supervised learning for sentiment categorization","key":"4"},{"doi-asserted-by":"publisher","key":"5","DOI":"10.1002\/asi.22724"},{"doi-asserted-by":"publisher","key":"6","DOI":"10.1162\/neco.2006.18.7.1527"},{"year":"2014","author":"Y. Kim","article-title":"Convolutional neural networks for sentence classification","key":"7"},{"year":"2015","author":"Y. Zhang","article-title":"A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification","key":"8"},{"key":"9","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/S0166-4115(97)80111-2","article-title":"Serial order: a parallel distributed processing approach","volume":"121","author":"Jordan","year":"1997","journal-title":"Advances in Psychology"},{"year":"2018","author":"J. Devlin","article-title":"Bert: pre-training of deep bidirec-tional transformers for language understanding","key":"10"},{"year":"2021","author":"Y. Lin","article-title":"BertGCN: transductive text classification by combining GCN and BERT","key":"11"},{"year":"2013","author":"A. Graves","article-title":"Generating sequences with recurrent neural networks","key":"12"},{"author":"D. Tang","first-page":"1422","article-title":"Document modeling with gated recurrent neural network for sentiment classification","key":"13"},{"doi-asserted-by":"publisher","key":"14","DOI":"10.1145\/3052770"},{"doi-asserted-by":"publisher","key":"15","DOI":"10.1016\/j.ins.2018.10.030"},{"doi-asserted-by":"publisher","key":"16","DOI":"10.1142\/s0218001419590468"},{"doi-asserted-by":"publisher","key":"17","DOI":"10.1088\/1742-6596\/1229\/1\/012062"},{"doi-asserted-by":"publisher","key":"18","DOI":"10.3233\/jcm-190022"},{"issue":"2","key":"19","first-page":"285","article-title":"Sentiment classification based on piecewise pooling convolutional neural network","volume":"56","author":"Y. Zhang","year":"2018","journal-title":"Computers, Materials and Continua"},{"author":"N. K. Thomas","article-title":"Semi-supervised classification with graph convolutional networks","key":"20"},{"author":"L. Yao","first-page":"7370","article-title":"Graph convolutional networks for text classification","key":"21"},{"author":"A. Joulin","first-page":"427","article-title":"Bag of tricks for efficient text classification","key":"22"},{"doi-asserted-by":"publisher","key":"23","DOI":"10.1016\/j.knosys.2020.106292"},{"doi-asserted-by":"publisher","key":"24","DOI":"10.1016\/j.ins.2022.03.082"},{"key":"25","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"M. Defferrard","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"year":"2013","author":"J. Bruna","article-title":"Spectral networks and locally connected networks on graphs","key":"26"},{"year":"2015","author":"M. Henaff","article-title":"Deep convolutional networks on graph-structured data","key":"27"},{"doi-asserted-by":"publisher","key":"28","DOI":"10.1016\/j.knosys.2022.109972"},{"key":"29","article-title":"Xlnet: generalized autoregressive pretraining for language understanding","volume":"32","author":"Z. Yang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"year":"2019","author":"Y. Liu","article-title":"RoBERTa: a robustly optimized BERT pretraining approach","key":"30"},{"doi-asserted-by":"publisher","key":"31","DOI":"10.1162\/tacl_a_00300"},{"author":"W. Wang","article-title":"StructBERT: incorporating language structures into pre-training for deep language understanding","key":"32"},{"author":"S. Sun","doi-asserted-by":"crossref","article-title":"Patient knowledge distillation for BERT model compression","key":"33","DOI":"10.18653\/v1\/D19-1441"},{"year":"2020","author":"Z. Sun","article-title":"MobileBERT: a compact task-agnostic BERT for resource-limited devices","key":"34"},{"year":"2020","author":"Y. You","article-title":"Large batch optimization for deep learning: training BERT in 76 minutes","key":"35"},{"year":"2020","author":"Z. Lan","article-title":"ALBERT: a lite BERT for self-supervised learning of language representations","key":"36"},{"year":"2020","author":"K. Clark","article-title":"ELECTRA: pre-training text encoders as discriminators rather than generators","key":"37"},{"key":"38","first-page":"22","article-title":"Word association norms, mutual information, and lexicography","volume":"16","author":"K. Church","year":"1990","journal-title":"Computational Linguistics"},{"year":"2016","author":"P. Liu","article-title":"Recurrent neural network for text classification with multi-task learning","key":"39"},{"doi-asserted-by":"publisher","key":"40","DOI":"10.1088\/1742-6596\/1207\/1\/012008"},{"year":"2015","author":"K. S. Tai","article-title":"Improved semantic representations from tree-structured long short-term memory networks","key":"41"}],"container-title":["Quantum Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/que\/2023\/3668960.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/que\/2023\/3668960.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/que\/2023\/3668960.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T17:35:14Z","timestamp":1699896914000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/que\/2023\/3668960\/"}},"subtitle":[],"editor":[{"given":"Shi Hai","family":"Dong","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":41,"alternative-id":["3668960","3668960"],"URL":"https:\/\/doi.org\/10.1155\/2023\/3668960","relation":{},"ISSN":["2577-0470"],"issn-type":[{"type":"electronic","value":"2577-0470"}],"subject":[],"published":{"date-parts":[[2023,11,13]]}}}