[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120921-en":3,"doc-seo-120921-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120921,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data","Twitter上的COVID-19议题讨论极为密集，研究人员通过情感与观点分析提取公众在疫情期间的态度线索。已有工作多聚焦于封控、政策措施或疫苗立场等特定方向，但缺少系统性的、面向应用场景的综述。本研究采用行为与社会科学视角，开展基于机器学习的情感分析系统文献综述，在五个数据库检索并筛选2019年10月至2022年1月的40篇论文。结果表明，准确率表现最优的是由多种分类器组成的集成模型；在Twitter数据上微调后，BERT与RoBERTa展现出最有前景的效果，为决策者与公共卫生专家提供可操作的应用指导。","Received 29 November 2022, accepted 2 January 2023, date of publication 3 February 2023, date of current version 16 February 2023. Digital Object Identifier 10.1109/ACCESS.2023.3242234  \nMachine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data  \nNIKLAS BRAIG1, ALINA BENZ1, SOEREN VOTH1, JOHANNES BREITENBACH1, AND RICARDO BUETTNER1,2,(Senior Member, IEEE)  \n1Chair of Information Systems and Data Science, University of Bayreuth, 95447 Bayreuth, Germany  \n2Fraunhofer FIT, 95444 Bayreuth, Germany  \nCorresponding author: Johannes Breitenbach ([johannes.breitenbach@uni-bayreuth.de](johannes.breitenbach@uni-bayreuth.de))  \nThis work was supported in part by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Grant 491183248, in part by the Federal Ministry for Economic Affairs and Climate Action [Bundesministerium für Wirtschaft und Klimaschutz (BMWK)] under Grant 16KN088849, and in part by the Open Access Publishing Fund of the University of Bayreuth.  \nABSTRACT On Twitter, COVID-19 is a highly discussed topic. People worldwide have used Twitter to express their viewpoints and feelings during the pandemic. Previous research has focused on particular topics such as the public’s sentiment during the lockdown, their opinion on governmental measures, or their stance towards COVID-19 vaccines. However, until today, there is no comprehensive overview that presents possible areas of application for sentiment analysis of COVID-19 Twitter data. Therefore, this study revealshow sentiment analysis can provide relevant insights for managing the pandemic by applying a behavioral and social science lens. In this context, our systematic literature review focuses on machine learning-based sentiment analysis techniques and compares the best-performing classification algorithms for COVID-19-related Twitter data. We performed a search in five databases, which are: IEEE Xplore DL, ScienceDirect, SpringerLink, ACM DL, and AIS Electronic Library. This search resulted in 40 papers published between October 2019 and January 2022 that used sentiment analysis to evaluate the public opinion on COVID-19-related topics, which we further investigated. Our research indicates that the best performing models in terms of accuracy are ensemble models that comprise various machine learning classifiers. Especially BERT and RoBERTa models provide the most promising results when fine-tuned on Twitter data. Our study aims to combine machine learning-based sentiment analysis and insights from social and behavioral science to provide decision-makers and public health experts with guidance on the application of sentiment analysis in the fight against the spread of COVID-19 .  \nINDEX TERMS Behavioral science, COVID-19, deep learning, machine learning, sentiment analysis, social science, twitter.  \nI. INTRODUCTION  \nResearchers from a variety of disciplines have rushed to provide solutions to mitigate the impact of the COVID-19 pandemic that has so far claimed the lives of more than five million people [1], [2] . Since the outbreak of COVID-19, social media has become pivotal in staying connected with family, friends, and colleagues, but also to stay informed and discuss new policy updates and regulations [3] .  \nGovernments and other organizations, such as the World The associate editor coordinating the review of this manuscript and  \napproving it for publication was Derek Abbott  .  \nHealth Organization (WHO), have used social media asa direct communication channel to disseminate information and manage the crisis [4], [5] . COVID-19 is, until today, one of the most discussed topics on Twitter. In the period from January to May 2020 alone, more than 120 million messages related to COVID-19 were published on Twitter [6] . This abundance of unfiltered Twitter data offers promising opportunities for public health research [7] . Besides, compared to other social media platforms, its uncomplicated access via the Twitter API makes ","cbCaisG0IBLPjk9d","https://ap.wps.com/l/cbCaisG0IBLPjk9d","pdf",5072739,1,26,"English","en",105,"# Abstract\n# Introduction\n## Social media as a communication channel\n## Sentiment analysis use cases for public health\n## Role of social and behavioral science\n# Related background and motivation","[{\"question\":\"该研究解决了什么缺口？\",\"answer\":\"以往研究虽关注封控情绪、政策观点或疫苗立场等单一主题，但缺乏对“COVID-19推特情感分析”的潜在应用领域进行系统概览的研究。\"},{\"question\":\"研究使用了怎样的系统性文献综述方法？\",\"answer\":\"在IEEE Xplore、ScienceDirect、SpringerLink、ACM DL和AIS Electronic Library等五个数据库中检索相关文献，并分析2019年10月至2022年1月发表的40篇论文。\"},{\"question\":\"哪些模型在准确率方面表现最好？\",\"answer\":\"准确率最优的通常是包含多种机器学习分类器的集成模型；在Twitter数据上微调后，BERT与RoBERTa提供了最有前景的结果。\"}]","Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data | PDF",1785732693,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-techniques-for-sentiment-analysis-of-covid-19-related-twitter-data","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-techniques-for-sentiment-analysis-of-covid-19-related-twitter-data/120921/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"该研究解决了什么缺口？","Question",{"text":76,"@type":77},"以往研究虽关注封控情绪、政策观点或疫苗立场等单一主题，但缺乏对“COVID-19推特情感分析”的潜在应用领域进行系统概览的研究。","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"研究使用了怎样的系统性文献综述方法？",{"text":81,"@type":77},"在IEEE Xplore、ScienceDirect、SpringerLink、ACM DL和AIS Electronic Library等五个数据库中检索相关文献，并分析2019年10月至2022年1月发表的40篇论文。",{"name":83,"@type":74,"acceptedAnswer":84},"哪些模型在准确率方面表现最好？",{"text":85,"@type":77},"准确率最优的通常是包含多种机器学习分类器的集成模型；在Twitter数据上微调后，BERT与RoBERTa提供了最有前景的结果。","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]