{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:43:52Z","timestamp":1778085832926,"version":"3.51.4"},"reference-count":58,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003600","name":"Korean National Police Agency","doi-asserted-by":"publisher","award":["NRF-2021R1F1A1061814"],"award-info":[{"award-number":["NRF-2021R1F1A1061814"]}],"id":[{"id":"10.13039\/501100003600","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["NRF-2021R1F1A1061814"],"award-info":[{"award-number":["NRF-2021R1F1A1061814"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Scientific Programming"],"published-print":{"date-parts":[[2021,10,26]]},"abstract":"<jats:p>Over the past few decades, text classification problems have been widely utilized in many real time applications. Leveraging the text classification methods by means of developing new applications in the field of text mining and Natural Language Processing (NLP) is very important. In order to accurately classify tasks in many applications, a deeper insight into deep learning methods is required as there is an exponential growth in the number of complex documents. The success of any deep learning algorithm depends on its capacity to understand the nonlinear relationships of the complex models within data. Thus, a huge challenge for researchers lies in the development of suitable techniques, architectures, and models for text classification. In this paper, hybrid deep learning models, with an emphasis on positioning of attention mechanism analysis, are considered and analyzed well for text classification. The first hybrid model proposed is called convolutional Bidirectional Long Short-Term Memory (Bi-LSTM) with attention mechanism and output (CBAO) model, and the second hybrid model is called convolutional attention mechanism with Bi-LSTM and output (CABO) model. In the first hybrid model, the attention mechanism is placed after the Bi-LSTM, and then the output Softmax layer is constructed. In the second hybrid model, the attention mechanism is placed after convolutional layer and followed by Bi-LSTM and the output Softmax layer. The proposed hybrid models are tested on three datasets, and the results show that when the proposed CBAO model is implemented for IMDB dataset, a high classification accuracy of 92.72% is obtained and when the proposed CABO model is implemented on the same dataset, a high classification accuracy of 90.51% is obtained.<\/jats:p>","DOI":"10.1155\/2021\/2420254","type":"journal-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T21:35:07Z","timestamp":1635284107000},"page":"1-12","source":"Crossref","is-referenced-by-count":7,"title":["Performance Analysis of Hybrid Deep Learning Models with Attention Mechanism Positioning and Focal Loss for Text Classification"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4019-2345","authenticated-orcid":true,"given":"Sunil Kumar","family":"Prabhakar","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harikumar","family":"Rajaguru","sequence":"additional","affiliation":[{"name":"Department of ECE, Bannari Amman Institute of Technology, Sathyamangalam 638401, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-6524","authenticated-orcid":true,"given":"Dong-Ok","family":"Won","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Hallym University, Chuncheon 24252, Gangwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59650-1_3"},{"key":"2","doi-asserted-by":"crossref","first-page":"2160","DOI":"10.1016\/j.proeng.2011.08.404","article-title":"An improvement to naive bayes for text classification","volume":"15","author":"Z. Wei","year":"2011","journal-title":"Procedia Engineering"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1023\/a:1012491419635"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45357-1_9"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2008.03.045"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1023\/a:1013681528748"},{"key":"7","first-page":"33","article-title":"A Survey on CNN and RNN implementations","author":"J. Hoffman"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.304"},{"key":"9","article-title":"Comparative study of CNN and RNN for natural language processing","author":"W. Yin","year":"2017"},{"key":"10","article-title":"Efficient estimation of word representations in vector space","author":"T. Mikolov","year":"2013"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"12","article-title":"Fasttext. zip: compressing text classification models","author":"A. Joulin","year":"2016"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p15-1162"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p15-1150"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045289"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"17","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"X. Zhang","year":"2015","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/iri.2016.61"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.033"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-2045"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.06.014"},{"key":"22","first-page":"3110","article-title":"Investigating capsule networks with dynamic routing for text classification","author":"W. Zhao"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1024"},{"key":"25","article-title":"Disan: directional self-attention network for rnn\/cnn-free language understanding","author":"T. Shen"},{"key":"26","article-title":"Learning natural language inference using bidirectional lstm model and inner-attention","author":"Y. Liu","year":"2016"},{"key":"27","article-title":"A structured self-attentive sentence embedding","author":"Z. Lin","year":"2017"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17-1038"},{"key":"29","article-title":"Ask me anything: dynamic memory networks for natural language processing","author":"A. Kumar"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186005"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"32","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"F. Wu"},{"key":"33","doi-asserted-by":"crossref","article-title":"Learning text similarity with siamese recurrent networks","author":"P. Neculoiu","DOI":"10.18653\/v1\/W16-1617"},{"key":"34","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"A. Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016285"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.10.065"},{"key":"37","article-title":"A c-lstm neural network for text classification","author":"C. Zhou","year":"2015"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1167"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1177"},{"key":"40","first-page":"364","article-title":"Hdltex: Hierarchical deep learning for text classification","author":"K. Kowsari"},{"key":"41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/k16-1006"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1109\/iscid.2018.00023"},{"key":"43","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07788-7"},{"key":"44","doi-asserted-by":"publisher","DOI":"10.1109\/iscid.2018.10144"},{"key":"45","doi-asserted-by":"publisher","DOI":"10.1109\/icaica.2019.8873454"},{"key":"46","first-page":"581","article-title":"Tree-structured regional CNN-LSTM model for dimensional sentiment analysis, \u201cIEEE\/ACM trans. Audio speech lang","volume":"28","author":"J. Wang","year":"2019","journal-title":"Processes"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2982538"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2954985"},{"key":"49","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.324"},{"key":"50","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"A. L. Maas"},{"key":"51","first-page":"90","article-title":"Baselines and bigrams: simple, good sentiment and topic classification","author":"S. Wang"},{"key":"52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1441"},{"key":"53","article-title":"GPU kernels for block-sparse weights","volume":"3","author":"S. Gray","year":"2017","journal-title":"Block-Sparse GPU Kernels"},{"key":"54","article-title":"Adversarial training methods for semi-supervised text classification","author":"T. Miyato","year":"2016"},{"key":"55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1052"},{"key":"57","article-title":"Compositional coding capsule network with k-means routing for text classification","author":"H. Ren","year":"2018"},{"key":"58","article-title":"Unsupervised data augmentation","author":"Q. Xie","year":"2019"}],"container-title":["Scientific Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/2420254.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/2420254.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/sp\/2021\/2420254.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T21:35:11Z","timestamp":1635284111000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/sp\/2021\/2420254\/"}},"subtitle":[],"editor":[{"given":"Sikandar","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":58,"alternative-id":["2420254","2420254"],"URL":"https:\/\/doi.org\/10.1155\/2021\/2420254","relation":{},"ISSN":["1875-919X","1058-9244"],"issn-type":[{"value":"1875-919X","type":"electronic"},{"value":"1058-9244","type":"print"}],"subject":[],"published":{"date-parts":[[2021,10,26]]}}}