{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:00:23Z","timestamp":1776884423455,"version":"3.51.2"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:00:00Z","timestamp":1648512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Polarity prediction is the field of study that discovers people\u2019s opinions, feelings, assessments, perspectives and feelings about associations and their attributes as communicated in written text. It is one of the most active research areas in the field of text mining. Nowadays online reviews play an important role by giving a helping hand to the customers to know about other customer\u2019s opinions about the product they are going to purchase. This also guides the organizations and government sectors to increase their quality of product and services. Pre-trained BERT (Bidirectional Encoder Representations from Transformers) is used for word embedding in this model. The fine-tuned BERT is used for better word representation which in turn improves the sentimental analysis classification accuracy. Bidirectional Long Short-Term Memory classifier is utilized for polarity prediction. To enhance the performance of Bidirectional Long Short-Term Memory, the weight parameters of Bi-directional LSTM are optimally selected by using APSO algorithm. Improved self-attention mechanism is added with BiLSTM for focusing on significant words in the context. For performance analysis, four bench mark datasets are used for experiments.<\/jats:p>","DOI":"10.1093\/comjnl\/bxac013","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T12:08:05Z","timestamp":1643112485000},"page":"1279-1294","source":"Crossref","is-referenced-by-count":36,"title":["An Improved Self Attention Mechanism Based on Optimized BERT-BiLSTM Model for Accurate Polarity Prediction"],"prefix":"10.1093","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9754-2604","authenticated-orcid":false,"given":"J","family":"Shobana","sequence":"first","affiliation":[{"name":"SRM Institute of Science and Technology , Ramapuram, Chennai 600089, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4478-2820","authenticated-orcid":false,"given":"M","family":"Murali","sequence":"additional","affiliation":[{"name":"SRM Institute of Science and Technology , Kattankulathur, Chennai 603203, India"}]}],"member":"286","published-online":{"date-parts":[[2022,3,29]]},"reference":[{"key":"2023052000434373700_ref1","first-page":"250","volume-title":"Proc. Semantic Computing (ICSC), IEEE International Conference","author":"David","year":"2014"},{"key":"2023052000434373700_ref2","first-page":"4","volume-title":"Social Media Mining: An Introduction","author":"Reza","year":"2014"},{"key":"2023052000434373700_ref3","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s00146-014-0549-4","article-title":"Social media analytics: a survey of techniques, tools and platforms","volume":"30","author":"Bogdan","year":"2015","journal-title":"AI Soc."},{"key":"2023052000434373700_ref4","volume-title":"Proc. IEEE International Conference on Electrical and Control Engineering","author":"Shipin","year":"2011"},{"key":"2023052000434373700_ref5","first-page":"452","volume-title":"3rd International Conference on Computing for Sustainable Global Development (INDIACom)","author":"Bakshi","year":"2016"},{"key":"2023052000434373700_ref6","first-page":"1","article-title":"Sentiment analysis and opinion mining","volume":"5","author":"Liu","year":"2012","journal-title":"Synt. Lect. Hum. Lang. Technol."},{"key":"2023052000434373700_ref7","volume-title":"Sentiment analysis of twitter data: a survey of techniques","author":"Kharde","year":"2016"},{"key":"2023052000434373700_ref8","first-page":"1","article-title":"Challenges of sentiment analysis in social networks: an overview","author":"Pozzi","year":"2017","journal-title":"Sentiment Anal Soc Netw"},{"key":"2023052000434373700_ref9","first-page":"1320","article-title":"Twitter as a corpus for sentiment analysis and opinion mining","volume":"10","author":"Pak","year":"2010","journal-title":"LREc"},{"key":"2023052000434373700_ref10","volume-title":"Word Embeddings for Natural Language Processing","author":"Lebret","year":"2016"},{"key":"2023052000434373700_ref11","first-page":"1","volume-title":"IEEE 7th International Conference on Adaptive Science & Technology (ICAST)","author":"Deho","year":"2018"},{"key":"2023052000434373700_ref12","doi-asserted-by":"crossref","first-page":"39948","DOI":"10.1109\/ACCESS.2019.2905252","article-title":"Skip-gram-KR: Korean word embedding for semantic clustering","volume":"7","author":"Ihm","year":"2019","journal-title":"IEEE Access"},{"key":"2023052000434373700_ref13","doi-asserted-by":"crossref","DOI":"10.1155\/2018\/9293437","article-title":"Automated text analysis based on skip-gram model for food evaluation in predicting consumer acceptance","author":"Kim","year":"2018","journal-title":"Comput. Intell. Neurosci."},{"key":"2023052000434373700_ref14","volume-title":"Word2vec parameter learning explained","author":"Rong","year":"2014"},{"key":"2023052000434373700_ref15","first-page":"1319","article-title":"Improving sentiment analysis: a combined approach","author":"Brahimi","year":"2019","journal-title":"J. King Saud Univ."},{"key":"2023052000434373700_ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-11716-4_12","article-title":"Automatic term extraction for sentiment classification of dynamically updated text collections into three classes","author":"Rubtsova","year":"2014","journal-title":"Commun. Comput. Informat. Sci"},{"key":"2023052000434373700_ref17","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1007\/s11518-019-5438-4","article-title":"DCWord: a novel deep learning approach to deceptive review identification by word vectors","volume":"28","author":"Zhang","year":"2019","journal-title":"J. Syst. Sci. Syst. Eng."},{"key":"2023052000434373700_ref18","doi-asserted-by":"crossref","first-page":"6625","DOI":"10.1007\/s00521-018-3477-2","article-title":"A novel feature extraction methodology for sentiment analysis of product reviews","volume":"31","author":"Chen","year":"2019","journal-title":"Neural Comput. Applic."},{"key":"2023052000434373700_ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-018-9943-9","article-title":"Dynamic network embedding via incremental skip-gram with negative sampling","volume":"63","author":"Peng","year":"2020","journal-title":"Sci. China Inf. Sci."},{"key":"2023052000434373700_ref20","first-page":"43612","article-title":"GLTM: a global and local word embedding-based topic model for short texts","author":"Liang","journal-title":"IEEE Access"},{"key":"2023052000434373700_ref21","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TNB.2018.2838137","article-title":"Phenotype extraction based on word embedding to sentence embedding cascaded approach","volume":"17","author":"Xing","year":"2018","journal-title":"IEEE Trans. Nanobioscience"},{"key":"2023052000434373700_ref22","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.eswa.2017.08.049","article-title":"W2VLDA: almost unsupervised system for aspect based sentiment analysis","volume":"91","author":"Garc\u00eda-Pablos","year":"2018","journal-title":"Exp. Syst. Appl."},{"key":"2023052000434373700_ref23","doi-asserted-by":"crossref","DOI":"10.1109\/TAFFC.2017.2717879","article-title":"A neural word embeddings approach for multi-domain sentiment analysis","volume":"8","author":"Dragoni","year":"2017","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2023052000434373700_ref24","first-page":"986","article-title":"Sentimental analysis of student feedback using machine learning techniques","volume":"8","author":"Dsouza","year":"2019","journal-title":"Int. J. Recent Technol. Eng."},{"key":"2023052000434373700_ref25","doi-asserted-by":"crossref","first-page":"3193","DOI":"10.1007\/s00500-015-2003-z","article-title":"Exploring mutual information-based sentimental analysis with kernel-based extreme learning machine for stock prediction","volume":"21","author":"Wang","year":"2017","journal-title":"Soft Comput."},{"key":"2023052000434373700_ref26","first-page":"2345","volume-title":"A Context-Based Model for Sentiment Analysis in Twitter","author":"Go","year":"2014"},{"key":"2023052000434373700_ref27","first-page":"157","article-title":"Scientific text sentiment analysis using machine learning techniques","volume":"10","author":"Raza","year":"2019","journal-title":"Int. J. Adv. Comput.Sci. Appl."},{"key":"2023052000434373700_ref28","first-page":"143","volume-title":"Invent. Commun. Comput. Technol.","author":"Salunke","year":"2021"},{"key":"2023052000434373700_ref29","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.eswa.2017.02.002","article-title":"Enhancing deep learning sentiment analysis with ensemble techniques in social applications","volume":"77","author":"Araque","year":"2017","journal-title":"Exp. Syst. Appl."},{"key":"2023052000434373700_ref30","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1007\/978-981-15-0187-6_17","article-title":"Microblog rumor detection based on comment sentiment and CNN-LSTM","author":"Lv","year":"2020","journal-title":"J. Artif. Intell. China"},{"key":"2023052000434373700_ref31","doi-asserted-by":"crossref","first-page":"4783","DOI":"10.1002\/cpe.4783","article-title":"Evaluating deep learning models for sentiment classification","volume":"30","author":"Karaku\u015f","year":"2018","journal-title":"Concurr. Comput."},{"key":"2023052000434373700_ref32","doi-asserted-by":"crossref","first-page":"3305","DOI":"10.1007\/s13369-018-3500-z","article-title":"Deep learning based sentiment analysis using convolution neural network","volume":"44","author":"Rani","year":"2019","journal-title":"Arab. J. Sci. Eng."},{"key":"2023052000434373700_ref33","article-title":"Exploration of social media for sentiment analysis using deep learning","author":"Chen","year":"2019","journal-title":"Soft Comput."},{"key":"2023052000434373700_ref34","first-page":"3","article-title":"Recurrent neural network based language model","volume":"2","author":"Mikolov","year":"2010","journal-title":"Dermatol. Int."},{"key":"2023052000434373700_ref35","first-page":"1","volume-title":"First International Conference on Secure Cyber Computing and Communication (ICSCCC)","author":"Kaur","year":"2018"},{"key":"2023052000434373700_ref36","first-page":"241","article-title":"Sentiment analysis of online movies\u2019 reviews using improved k-nearest neighbor classifier","volume":"3","author":"Arora","year":"2016","journal-title":"Adv. Comput. Sci. Inf. Technol."},{"key":"2023052000434373700_ref37","article-title":"Stock closing price prediction based on sentiment analysis and LSTM","author":"Jin","year":"2019","journal-title":"Neural Comput. Applic."},{"key":"2023052000434373700_ref38","first-page":"2169","article-title":"Lexicon-enhanced LSTM with attention for general sentiment analysis","volume":"6","author":"Xianghua","year":"2018","journal-title":"IEEE"},{"key":"2023052000434373700_ref39","doi-asserted-by":"publisher","first-page":"2169","DOI":"10.1109\/Access.2019.2909919","article-title":"Sentiment analysis of comment texts based on BiLSTM","volume":"7","author":"Guixian","year":"2019","journal-title":"IEEE"},{"key":"2023052000434373700_ref40","doi-asserted-by":"publisher","first-page":"11279","DOI":"10.1109\/ACCESS.2020.2965575","article-title":"Text summarization method based on double attention pointer network","volume":"8","author":"Li","year":"2020","journal-title":"IEEE"},{"key":"2023052000434373700_ref41","doi-asserted-by":"publisher","DOI":"10.1109\/Access.2019.2896621","volume-title":"An Enhanced LSTM for Trend Following of Time Series","author":"Yao","year":"2019"},{"key":"2023052000434373700_ref42","first-page":"695","article-title":"Opposition-based learning: a new scheme for machine intelligence. In international conference on computational intelligence for modelling, control and automation and international conference on intelligent agents, web technologies and internet commerce (CIMCA-IAWTIC'06)","volume":"1","author":"Tizhoosh","year":"2005","journal-title":"IEEE"},{"key":"2023052000434373700_ref43","doi-asserted-by":"publisher","first-page":"138603","DOI":"10.1109\/ACCESS.2019.2941964","article-title":"MS-pointer network: abstractive text summary based on multi-head self-attention","volume":"7","author":"Guo","year":"2019","journal-title":"IEEE"},{"key":"2023052000434373700_ref44","doi-asserted-by":"publisher","first-page":"92659","DOI":"10.1109\/ACCESS.2020.2994092","article-title":"Generative text summary based on enhanced semantic attention and gain-benefit gate","volume":"8","author":"Ding","year":"2020","journal-title":"IEEE"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/5\/1279\/50397604\/bxac013.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/66\/5\/1279\/50397604\/bxac013.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,20]],"date-time":"2023-05-20T00:45:36Z","timestamp":1684543536000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/66\/5\/1279\/6555411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,29]]},"references-count":44,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,3,29]]},"published-print":{"date-parts":[[2023,5,19]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxac013","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,5]]},"published":{"date-parts":[[2022,3,29]]}}}