{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:06:04Z","timestamp":1772643964367,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T00:00:00Z","timestamp":1659571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hunan Province Key R&amp;D Program","award":["2022NK2048"],"award-info":[{"award-number":["2022NK2048"]}]},{"name":"Hunan Province Key R&amp;D Program","award":["2020JJ4142"],"award-info":[{"award-number":["2020JJ4142"]}]},{"name":"Natural Science Foundation of Hunan Province","award":["2022NK2048"],"award-info":[{"award-number":["2022NK2048"]}]},{"name":"Natural Science Foundation of Hunan Province","award":["2020JJ4142"],"award-info":[{"award-number":["2020JJ4142"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>With the rise of mobile social networks, an increasing number of consumers are shopping through Internet platforms. The information asymmetry between consumers and producers has caused producers to misjudge the positioning of agricultural products in the market and damaged the interests of consumers. This imbalance between supply and demand is detrimental to the development of the agricultural market. Sentiment tendency analysis of after-sale reviews of agricultural products on the Internet could effectively help consumers evaluate the quality of agricultural products and help enterprises optimize and upgrade their products. Targeting problems such as non-standard expressions and sparse features in agricultural product reviews, this paper proposes a sentiment analysis algorithm based on an improved Bidirectional Encoder Representations from Transformers (BERT) model with symmetrical structure to obtain sentence-level feature vectors of agricultural product evaluations containing complete semantic information. Specifically, we propose a recognition method based on speech rules to identify the emotional tendencies of consumers when evaluating agricultural products and extract consumer demand for agricultural product attributes from online reviews. Our results showed that the F1 value of the trained model reached 89.86% on the test set, which is an increase of 7.05 compared with that of the original BERT model. The agricultural evaluation classification algorithm proposed in this paper could efficiently determine the emotion expressed by the text, which helps to further analyze network evaluation data, extract effective information, and realize the visualization of emotion.<\/jats:p>","DOI":"10.3390\/sym14081604","type":"journal-article","created":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T02:12:39Z","timestamp":1659665559000},"page":"1604","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["A Study of Sentiment Analysis Algorithms for Agricultural Product Reviews Based on Improved BERT Model"],"prefix":"10.3390","volume":"14","author":[{"given":"Ying","family":"Cao","sequence":"first","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China"},{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-1595","authenticated-orcid":false,"given":"Zhexing","family":"Sun","sequence":"additional","affiliation":[{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Ling","family":"Li","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China"}]},{"given":"Weinan","family":"Mo","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China"},{"name":"Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650500, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1561\/2000000039","article-title":"Deep Learning: Methods and Applications","volume":"7","author":"Deng","year":"2014","journal-title":"Found. Trends Signal Process."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., and Zettlemoyer, L. (2018, January 1\u20136). Deep Contextualized Word Representations. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), New Orleans, LA, USA.","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"107259","DOI":"10.1016\/j.knosys.2021.107259","article-title":"Customer preferences extraction for air purifiers based on fine-grained sentiment analysis of online reviews","volume":"228","author":"Zhang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105004","DOI":"10.1016\/j.knosys.2019.105004","article-title":"Dual memory network model for sentiment analysis of review text","volume":"188","author":"Shen","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.knosys.2012.08.003","article-title":"Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon","volume":"37","author":"Xianghua","year":"2013","journal-title":"Knowl.-Based Syst."},{"key":"ref_6","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"103706","DOI":"10.1016\/j.scs.2022.103706","article-title":"CitEnergy: A BERT based model to analyse Citizens\u2019 Energy-Tweets","volume":"80","author":"Bedi","year":"2022","journal-title":"Sustain. Cities Soc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102872","DOI":"10.1016\/j.ipm.2022.102872","article-title":"Predictive intelligence in harmful news identification by BERT-based ensemble learning model with text sentiment analysis","volume":"59","author":"Lin","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.ins.2015.03.040","article-title":"Sentiment analysis: A review and comparative analysis of web services","volume":"311","author":"Olivas","year":"2015","journal-title":"Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.eswa.2016.11.022","article-title":"Company event popularity for financial markets using Twitter and sentiment analysis","volume":"71","author":"Daniel","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Popescu, A.-M., and Etzioni, O. (2005, January 6\u20138). Extracting product features and opinions from reviews. Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, Vancouver, BC, Canada.","DOI":"10.3115\/1220575.1220618"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5995","DOI":"10.1016\/j.eswa.2014.03.022","article-title":"Feature-based opinion mining through ontologies","volume":"41","author":"Moreno","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhao, L., Huang, M., Sun, J., Luo, H., Yang, X., and Zhu, X. (2015, January 18\u201323). Sentiment Extraction by Leveraging Aspect-Opinion Association Structure. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Melbourne, Australia.","DOI":"10.1145\/2806416.2806525"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.dss.2012.12.028","article-title":"The impact of social and conventional media on firm equity value: A sentiment analysis approach","volume":"55","author":"Yu","year":"2013","journal-title":"Decis. Support Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s11280-015-0381-x","article-title":"Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier","volume":"20","author":"Manek","year":"2016","journal-title":"World Wide Web"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.knosys.2017.03.020","article-title":"Feature selection and ensemble construction: A two-step method for aspect based sentiment analysis","volume":"125","author":"Akhtar","year":"2017","journal-title":"Knowl.-Based Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1016\/j.chb.2014.11.090","article-title":"Sentiment detection in social networks and in collaborative learning environments","volume":"51","author":"Colace","year":"2015","journal-title":"Comput. Hum. Behav."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.eswa.2016.10.043","article-title":"Sentiment analysis leveraging emotions and word embeddings","volume":"69","author":"Giatsoglou","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lee, L.-H., Lu, Y., Chen, P.-H., Lee, P.-L., and Shyu, K.-K. (2019, January 1). NCUEE at MEDIQA 2019: Medical Text Inference Using Ensemble BERT-BiLSTM-Attention Model. Proceedings of the 18th BioNLP Workshop and Shared Task, Florence, Italy.","DOI":"10.18653\/v1\/W19-5058"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ohsugi, Y., Saito, I., Nishida, K., Asano, H., and Tomita, J. (2019). A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension. arXiv.","DOI":"10.18653\/v1\/W19-4102"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.neucom.2021.07.002","article-title":"BERT-JAM: Maximizing the utilization of BERT for neural machine translation","volume":"460","author":"Zhang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/LSP.2021.3139856","article-title":"MF-BERT: Multimodal Fusion in Pre-Trained BERT for Sentiment Analysis","volume":"29","author":"He","year":"2022","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1093\/jamia\/ocz164","article-title":"Traditional Chinese medicine clinical records classification with BERT and domain specific corpora","volume":"26","author":"Yao","year":"2019","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_24","unstructured":"Zhang, C., and Abdul-Mageed, M. (August, January 28). No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects. Proceedings of the Fourth Arabic Natural Language Processing Workshop, Florence, Italy."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Kondratyuk, D. (2019, January 2). Cross-Lingual Lemmatization and Morphology Tagging with Two-Stage Multilingual BERT Fine-Tuning. Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, Florence, Italy.","DOI":"10.18653\/v1\/W19-4203"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Ma, Z., Gao, L., and Xu, Y. (2020). An ERNIE-Based Joint Model for Chinese Named Entity Recognition. Appl. Sci., 10.","DOI":"10.3390\/app10165711"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5016","DOI":"10.1007\/s10489-020-02101-8","article-title":"Sentiment analysis of Chinese stock reviews based on BERT model","volume":"51","author":"Li","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"162004","DOI":"10.1109\/ACCESS.2020.3019500","article-title":"Tree Framework with BERT Word Embedding for the Recognition of Chinese Implicit Discourse Relations","volume":"8","author":"Jiang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_29","first-page":"69","article-title":"Relation Classification Based on Information Enhanced BERT","volume":"35","author":"Wan","year":"2021","journal-title":"J. Chin. Inf. Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, T., Chen, Y., Lv, M., He, G., Zhu, T., Wang, T., and Weng, Z. (2021). A Payload Based Malicious HTTP Traffic Detection Method Using Transfer Semi-Supervised Learning. Appl. Sci., 11.","DOI":"10.3390\/app11167188"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Rizwan, A., Iqbal, N., Ahmad, R., and Kim, D.-H. (2021). WR-SVM Model Based on the Margin Radius Approach for Solving the Minimum Enclosing Ball Problem in Support Vector Machine Classification. Appl. Sci., 11.","DOI":"10.3390\/app11104657"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Choi, S. (2020). Combined kNN Classification and Hierarchical Similarity Hash for Fast Malware Detection. Appl. Sci., 10.","DOI":"10.3390\/app10155173"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Oh, H.-J., Syifa, M., Lee, C.-W., and Lee, S. (2019). Land Subsidence Susceptibility Mapping Using Bayesian, Functional, and Meta-Ensemble Machine Learning Models. Appl. Sci., 9.","DOI":"10.3390\/app9061248"},{"key":"ref_34","first-page":"124","article-title":"A Novel Financial Text Sentiment Analysis-Based Approach for Stock Index Prediction","volume":"38","author":"Xu","year":"2021","journal-title":"Quant. Tech. Econ."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Leng, J., Wang, D., Ma, X., Yu, P., Wei, L., and Chen, W. (2022). Bi-level artificial intelligence model for risk classification of acute respiratory diseases based on Chinese clinical data. Appl. Intell., 1\u201318.","DOI":"10.1007\/s10489-022-03222-y"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Hsieh, Y., and Zeng, X. (2022). Sentiment Analysis: An ERNIE-BiLSTM Approach to Bullet Screen Comments. Sensors, 22.","DOI":"10.3390\/s22145223"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"032097","DOI":"10.1088\/1742-6596\/1345\/3\/032097","article-title":"Improved text sentiment classification method based on BiGRU-attention","volume":"1345","author":"Zhou","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"8697","DOI":"10.3233\/JIFS-192078","article-title":"Aspect-based sentiment analysis in Chinese based on mobile reviews for BiLSTM-CRF","volume":"40","author":"Miao","year":"2021","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_39","first-page":"504","article-title":"Online Comments Analysis and Its Application Research Progress in E-commerce of Fresh Agricultural Products","volume":"52","author":"Feng","year":"2021","journal-title":"Trans. Chin. Soc. Agric. Mach."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/8\/1604\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:03:59Z","timestamp":1760141039000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/8\/1604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,4]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["sym14081604"],"URL":"https:\/\/doi.org\/10.3390\/sym14081604","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,4]]}}}