%0期刊文章%@ 1438-8871 %I JMIR出版物%V 23%卡塔尔世界杯8强波胆分析 N 9% P e30451% T识别虚假的人乳头瘤病毒(HPV)疫苗信息和相应的风险感知来自Twitter:先进的预测模型%A Tomaszewski,Tre %A Morales,Alex %A Lourentzou,Ismini %A Caskey,Rachel %A Liu,Bing %A Schwartz,Alan %A Chin,Jessie %+伊利诺伊大学香槟分校信息科学学院，501 E Daniel St, Champaign, IL, 61820，美国，1 217 333 0125，chin5@illinois.edu %K错误信息%K虚假信息%K社交媒体%K HPV %K人乳头瘤病毒疫苗接种%K疫苗接种%K因果关系挖掘%K原因%K效果%K风险感知%K疫苗%K感知%K风险%K推特%K机器学习%K自然语言处理%K宫颈癌%D 2021 %7 9.9.2021 %9原始论文%J J医学互联网Res %G英语%X背景:人类乳头瘤病毒(HPV)疫苗的接种率仍然很低，尽管HPV疫苗的有效性已经确立了十多年。疫苗犹豫的部分原因是社交媒体上关于HPV疫苗的虚假信息。打击虚假的HPV疫苗信息是解决疫苗犹豫的合理步骤。目的:鉴于虚假HPV疫苗信息的巨大危害，迫切需要在虚假社交媒体信息传播之前识别出来。这项研究的目标是开发一种系统和可推广的方法来识别社交媒体上的虚假HPV疫苗信息。方法:本研究利用机器学习和自然语言处理开发了一系列分类模型和因果关系挖掘方法，以识别和检查Twitter上HPV疫苗相关的真假信息。结果:我们发现卷积神经网络模型在识别包含虚假HPV疫苗相关信息的推文方面优于所有其他模型(F得分=91.95)。 We also developed completely unsupervised causality mining models to identify HPV vaccine candidate effects for capturing risk perceptions of HPV vaccines. Furthermore, we found that false information contained mostly loss-framed messages focusing on the potential risk of vaccines covering a variety of topics using more diverse vocabulary, while true information contained both gain- and loss-framed messages focusing on the effectiveness of vaccines covering fewer topics using relatively limited vocabulary. Conclusions: Our research demonstrated the feasibility and effectiveness of using predictive models to identify false HPV vaccine information and its risk perceptions on social media. %M 34499043 %R 10.2196/30451 %U //www.mybigtv.com/2021/9/e30451 %U https://doi.org/10.2196/30451 %U http://www.ncbi.nlm.nih.gov/pubmed/34499043

map