{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:52:58Z","timestamp":1782834778780,"version":"3.54.5"},"reference-count":22,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,8,15]],"date-time":"2021-08-15T00:00:00Z","timestamp":1628985600000},"content-version":"vor","delay-in-days":226,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005089","name":"Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["4204100"],"award-info":[{"award-number":["4204100"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010818","name":"Beijing Information Science and Technology University","doi-asserted-by":"publisher","award":["1825023"],"award-info":[{"award-number":["1825023"]}],"id":[{"id":"10.13039\/501100010818","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010818","name":"Beijing Information Science and Technology University","doi-asserted-by":"publisher","award":["5112111004"],"award-info":[{"award-number":["5112111004"]}],"id":[{"id":"10.13039\/501100010818","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>The mobile social network contains a large amount of information in a form of commentary. Effective analysis of the sentiment in the comments would help improve the recommendations in the mobile network. With the development of well\u2010performing pretrained language models, the performance of sentiment classification task based on deep learning has seen new breakthroughs in the past decade. However, deep learning models suffer from poor interpretability, making it difficult to integrate sentiment knowledge into the model. This paper proposes a sentiment classification model based on the cascade of the BERT model and the adaptive sentiment dictionary. First, the pretrained BERT model is used to fine\u2010tune with the training corpus, and the probability of sentiment classification in different categories is obtained through the softmax layer. Next, to allow a more effective comparison between the probabilities for the two classes, a nonlinearity is introduced in a form of positive\u2010negative probability ratio, using the rule method based on sentiment dictionary to deal with the probability ratio below the threshold. This method of cascading the pretrained model and the semantic rules of the sentiment dictionary allows to utilize the advantages of both models. Different sized Chnsenticorp data sets are used to train the proposed model. Experimental results show that the Dict\u2010BERT model is better than the BERT\u2010only model, especially when the training set is relatively small. The improvement is obvious with the accuracy increase of 0.8%.<\/jats:p>","DOI":"10.1155\/2021\/8785413","type":"journal-article","created":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T05:28:25Z","timestamp":1629091705000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Sentiment Classification Algorithm Based on the Cascade of BERT Model and Adaptive Sentiment Dictionary"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4478-1692","authenticated-orcid":false,"given":"Ruixue","family":"Duan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-0728","authenticated-orcid":false,"given":"Zhuofan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0280-8455","authenticated-orcid":false,"given":"Yangsen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9303-3682","authenticated-orcid":false,"given":"Xiulei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8390-6649","authenticated-orcid":false,"given":"Yue","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,8,15]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4000"},{"key":"e_1_2_9_2_2","first-page":"93","article-title":"Chinese micro-blog sentiment analysis based on multiple sentiment dictionaries and semantic rule sets","volume":"36","author":"Wu J. S.","year":"2019","journal-title":"Computer Applications and Software"},{"key":"e_1_2_9_3_2","first-page":"94","article-title":"Sentiment analysis based on emotion commonsense knowledge","volume":"33","author":"Yang L.","year":"2019","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_2_9_4_2","first-page":"2914","article-title":"Research of micro-blog short text sentiment orientation analysis based on semantic","volume":"33","author":"Ma L.","year":"2016","journal-title":"Application Research of Computers"},{"key":"e_1_2_9_5_2","first-page":"238","article-title":"Sentiment analysis of Chinese micro-blog based on topic","volume":"41","author":"Wei H.","year":"2015","journal-title":"Computer Engineering"},{"key":"e_1_2_9_6_2","first-page":"1879","article-title":"News named entity recognition and sentiment classification based on attention-based bi-directional long short-term memory neural network and conditional random field","volume":"40","author":"Hu T.","year":"2020","journal-title":"Journal of Computer Applications"},{"key":"e_1_2_9_7_2","unstructured":"DevlinJ. ChangM. W. LeeK. andToutanovaK. BERT: pre-training of deep bidirectional transformers for language understanding 2018 https:\/\/arxiv.org\/abs\/1810.04805."},{"key":"e_1_2_9_8_2","first-page":"3084","article-title":"Sentiment analysis of movie reviews based on dictionary and weak tagging information","volume":"38","author":"Zhen F.","year":"2018","journal-title":"Journal of Computer Applications"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"PangB. LeeL. L. andShivakumarV. Thumbs up: sentiment classification using machine learning techniques In the proceeding of EMNLP 2002 Philadelphia USA 79\u201386.","DOI":"10.3115\/1118693.1118704"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"KimS. M.andHoyyE. Automatic identification of pro and con reasons in online reviews Proceedings of the international conference on computational linguistics (COLING) and the Association for computational Linguistics (ACL): Posters 2006 Sydney Australia 483\u2013490.","DOI":"10.3115\/1273073.1273136"},{"key":"e_1_2_9_11_2","first-page":"73","article-title":"Hierarchical structure based hybrid approach to sentiment analysis of Chinese micro blog and its feature extraction","volume":"2012","author":"Xie L.","year":"2012","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_2_9_12_2","first-page":"1","article-title":"Empirical study of sentiment classification for Chinese microblog based on machine learning","volume":"2012","author":"Liu Z. M.","year":"2012","journal-title":"Computer Engineering and Applications"},{"key":"e_1_2_9_13_2","unstructured":"MikolovT. ChenK. CorradoG. andDeanJ. Efficient estimation of word representations in vector space In proceddings of International Conference on Learning Representations 2013 Scottsdale Arizona USA."},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-017-1759-2"},{"key":"e_1_2_9_15_2","unstructured":"LanZ. ChenM. GoodmanS. GimpelK. SharmaP. andSoricutR. ALBERT: a lite BERT for self-supervised learning of language representations 2019 https:\/\/arxiv.org\/abs\/1909.11942."},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/8959635"},{"key":"e_1_2_9_17_2","first-page":"742","article-title":"Topic words extraction of social media based on semantic constrained and time associated LDA","volume":"39","author":"Wan H. X.","year":"2018","journal-title":"Journal of Chinese Computer Systems"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"ZhangY. FuJ. SheD. ZhangY. WangS. andYangJ. Text emotion distribution learning via multi-task convolutional neural network International Joint Conference on Artificial Intelligence 2018 Stockholm Sweden 4595\u20134601.","DOI":"10.24963\/ijcai.2018\/639"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.09.048"},{"key":"e_1_2_9_20_2","first-page":"1","article-title":"Slang SD: building and using a sentiment dictionary of slang words for short-text sentiment classification","volume":"2016","author":"Wu L.","year":"2016","journal-title":"Language Resources & Evaluation"},{"key":"e_1_2_9_21_2","unstructured":"Chnsenticorp data https:\/\/github.com\/duanruixue\/Chnsenticorp."},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2948068"}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/8785413.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/8785413.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8785413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T09:45:32Z","timestamp":1723023932000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8785413"}},"subtitle":[],"editor":[{"given":"Jinbo","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8785413"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8785413","archive":["Portico"],"relation":{},"ISSN":["1530-8669","1530-8677"],"issn-type":[{"value":"1530-8669","type":"print"},{"value":"1530-8677","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-05-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8785413"}}