Sentiment Analysis of Online Healthy Community Based on Semantic Enhancement

Authors

Pu HAN, 1.School of Management，Nanjing University of Posts & Telecommunications, Nanjing 210003 2.Jiangsu Provincial Key Laboratory of Data Engineering and Knowledge Service, Nanjing 210023
YE Dongyu, School of Management，Nanjing University of Posts & Telecommunications, Nanjing 210003

Keywords

sentiment analysis, dependency parsing, graph neural networks, semantic enhancement, BERT-TBGH, online health communities

Abstract

[Purpose/significance]In order to make full use of the value of text dependent syntactic information and prior emotion knowledge in emotion analysis， a semantic enhanced online healthy community emotion analysis model was proposed. [Method/process]Firstly， feature vectors for pre-processed online health community data are generated by Word2Vec and BERT; then local and global information of online review text are extracted using TextCNN and BiLSTM respectively based on dual-channel idea; then sentiment knowledge and dependency grammar information are merged in graph attention networks for semantic enhancement; finally， dual-channel features are fused and perform online health community sentiment classification in fully connected layer. [Result/conclusion]The comparative experiments on 31718 online health community comments show that the accuracy of the BERT-TBGH model based on semantic enhancement reaches 90.77%, which is 10.57% and 7.79% higher than the classical models TextCNN and BiLSTM and is 1.85% and 1.00% higher after introducing sentiment knowledge and character-level dependency syntactic information. The proposed model based on semantic enhanced BERT-TBGH model can effectively improve the effect of online healthy community emotion analysis. The defect of this article is that the experiment was limited to the online health community dataset and was not further validated on larger datasets.

First Page

88

Recommended Citation

HAN, Pu and Dongyu, YE (2024) "Sentiment Analysis of Online Healthy Community Based on Semantic Enhancement," Scientific Information Research: Vol. 6: Iss. 2, Article 8.
Available at: https://eng.kjqbyj.com/journal/vol6/iss2/8

Reference

[1] 国务院.国务院关于实施健康中国行动的意见[N].人民日报，2019-07-16（007）. [2] 国务院办公厅.国务院办公厅关于促进“互联网+医疗健康”发展的意见[EB/OL].（2018-04-25）[2023-03-06].https://www.gov.cn/gongbao/content/2018/content_5291365.htm. [3] 杨善林，丁帅，顾东晓，等.医疗健康大数据驱动的知识发现与知识服务方法[J].管理世界，2022，38（01）：219-229. [4] 李静，刘德喜，万常选，等.社会网络用户心理健康自动评估研究综述[J].中文信息学报，2021，35（02）：19-32. [5] ZUNIC A，CORCORAN P，SPASIC I.Sentiment Analysis in Health and Well-Being：Systematic Review[J].JMIR Medical Informatics，2020，8（01）：e16023. [6] 周欢，刘嘉，张培颖，等.复杂网络视角下在线健康社区评论有用性研究[J].情报科学，2022，40（09）：88-97. [7] HAO H，ZHANG K.The Voice of Chinese Health Consumers：A Text Mining Approach to Web-based Physician Reviews[J].Journal of Medical Internet Research，2016，18（05）：e108. [8] CAVALCANTI D，PRUDÊNCIO R.Aspect-Based Opinion Mining in Drug Reviews[C]//Portuguese Conference on Artificial Intelligence，São Paulo：Springer，2017. [9] 陈忆金，陈佳文，古婷骅，等.健康信息用户探索式搜索过程中的情感体验状态与变化研究[J].情报资料工作，2022，43（04）：52-60. [10] JAMES T L，CALDERON E D V，COOK D F.Exploring Patient Perceptions of Healthcare Service Quality through Analysis of Unstructured Feedback[J].Expert Systems with Applications，2017（71）：479-492. [11] WILEY M T，JIN C，HRISTIDIS V，et al.Pharmaceutical drugs chatter on Online Social Networks[J].Journal of Biomedical Informatics，2014（49）：245-254. [12] 王帅，纪雪梅.基于在线健康社区用户画像的情感表达特征研究[J].情报理论与实践，2022，45（06）：179-187. [13] TABOADA M，BROOKE J，TOFILOSKI M，et al.Lexicon-Based Methods for Sentiment Analysis[J].Computational linguistics，2011，37（02）：267-307. [14] ESULI A，SEBASTIANI F.Sentiwordnet：A Publicly Available Lexical Resource for Opinion Mining[C]//Proceedings of the Fifth International Conference on Language Resources and Evaluation（LREC 06），Paris：European Language Resources Association，2006. [15] PARK S，LEE J，KIM K.Semi-supervised distributed representations of documents for sentiment analysis[J].Neural Networks，2019（119）：139-150. [16] ZHANG K，XIE Y，YANG Y，et al.Incorporating Conditional Random Fields and Active Learning to Improve Sentiment Identification[J].Neural Networks，2014（58）：60-67. [17] MISHRA A，MALVIYA A，AGGARWAL S.Towards Automatic Pharmacovigilance：Analyzing Patient Reviews and Sentiment on Oncological Drugs[C]//IEEE International Conference on Data Mining Workshop，Atlantic City，NJ：IEEE，2015. [18] GREAVES F，RAMIREZ-CANO D，MILLETT C，et al.Use of Sentiment Analysis for Capturing Patient Experience from Free-Text Comments Posted Online[J].Journal of Medical Internet Research，2013，15（11）：e239. [19] 吴鹏，应杨，沈思.基于双向长短期记忆模型的网民负面情感分类研究[J].情报学报，2018，37（08）：845-853. [20] JELODAR H，WANG Y，ORJI R，et al.Deep Sentiment Classification and Topic Discovery on Novel Coronavirus or COVID-19 Online Discussions：NLP Using LSTM Recurrent Neural Network Approach[J].IEEE Journal of Biomedical and Health Informatics，2020，24（10）：2733-2742. [21] 叶艳，吴鹏，周知，等.基于LDA-BiLSTM模型的在线医疗服务质量识别研究[J].情报理论与实践，2022，45（08）：178-183，168. [22] HU X，LIU B，SHU L，et al.BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis[C]//In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics：Human Language Technologies，Minneapolis，2019（01）：2324-2335. [23] SUN C，HUANG L，QIU X.Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence[C]//2019 Association for Computational Linguistics，Minneapolis，2019：380-385. [24] 何旭，杨柳，邓春林.基于方面级情感分析的红色旅游目的地形象感知研究[J].科技情报研究，2022，4（04）：78-88. [25] 刘继，顾凤云.基于BERT与BiLSTM混合方法的网络舆情非平衡文本情感分析[J].情报杂志，2022，41（04）：104-110. [26] BISEDA B，MO K.Enhancing Pharmacovigilance with Drug Reviews and Social Media[J/OL].（2020-04-18）[2023-03-06].https://arxiv.org/ftp/arxiv/papers/2004/2004.08731.pdf. [27] COLÓN-RUIZ C，SEGURA-BEDMAR I.Comparing deep learning architectures for sentiment analysis on drug reviews[J].Journal of Biomedical Informatics，2020（110）：103539. [28] 唐晓波，刘一平.基于依存句法的跨语言细粒度情感分析[J].情报理论与实践，2018，41（06）：124-129. [29] 聂卉，首欢容.基于修正点互信息的特征级情感词极性自动研判[J].图书情报工作，2020，64（05）：114-123. [30] 王娟，曹树金，谢建国.基于短语句法结构和依存句法分析的情感评价单元抽取[J].情报理论与实践，2017，40（03）：107-113. [31] 由丽萍，何玲玲.基于框架语义的在线医疗评论情感分析[J].现代情报，2020，40（03）：111-116，125. [32] 周雨婷，代金鞘，刘嘉勇，等.一种基于语义增强和指导路由机制的方面级情感三元组抽取方法[J].四川大学学报（自然科学版），2023，60（05）：112-120. [33] 张雪，赵晖.基于多事件语义增强的情感分析[J].计算机科学，2023，50（05）：238-247. [34] 汪红松，李嘉展，叶浩贤，等.结合语法增强与噪声削减的方面级情感分析模型[J/OL].计算机工程与应用:1-11[2023-10-21].http://kns.cnki.net/kcms/detail/11.2127.TP.20230523.1748.012.html. [35] WU H，HUANG C，DENG S.Improving aspect-based sentiment analysis with Knowledge-aware Dependency Graph Network[J].Information Fusion，2023（92）：289-299. [36] 陈轶洲，刘旭生，孙林檀，等.基于图神经网络的社交网络影响力预测算法[J].南京大学学报（自然科学），2022，58（03）：386-397. [37] 赵志影，邵新慧，林幸.用于方面情感分析的结合图卷积神经网络的注意力模型[J].中文信息学报，2022，36（07）：154-163. [38] 范涛，王昊，吴鹏.基于图卷积神经网络和依存句法分析的网民负面情感分析研究[J].数据分析与知识发现，2021，5（09）：97-106. [39] WU H，ZHANG Z，SHI S，et al.Phrase dependency relational graph attention network for Aspect-based Sentiment Analysis[J].Knowledge-Based Systems，2022（236）：107736. [40] 刘阳光，岂凡超，刘知远，等.HowNet义原标注一致性检验方法研究[J].中文信息学报，2021，35（04）：23-34. [41] 王文，王树锋，李洪华.基于文本语义和表情倾向的微博情感分析方法[J].南京理工大学学报，2014，38（06）：733-738，749. [42] 王晰巍，邢云菲，韦雅楠，等.大数据驱动的社交网络舆情用户情感主题分类模型构建研究：以“移民”主题为例[J].信息资源管理学报，2020，10（01）：29-38，48. [43] ZHANG Y，WALLACE B.A Sensitivity Analysis of Convolutional Neural Networks for Sentence Classification[J].arXiv preprint arXiv：1510.03820，2015. [44] CHE W X， LI Z H， LIU T.LTP：A Chinese Language Technology Platform[C]//Proceedings of the 23rd International Conference on Computational Linguistics，Beijing：Coling 2010 Organizing Committee，2010：13-16. [45] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is All you Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems，Vancouver：2017：6000-6010.