With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can a...With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can also reduce difficulties in management of online public opinions.A convolutional neural network model based on multi-head attention is proposed to solve the problem of how to effectively model relations among words and identify key words in emotion classification tasks with short text contents and lack of complete context information.Firstly,encode word positions so that order information of input sequences can be used by the model.Secondly,use a multi-head attention mechanism to obtain semantic expressions in different subspaces,effectively capture internal relevance and enhance dependent relationships among words,as well as highlight emotional weights of key emotional words.Then a dilated convolution is used to increase the receptive field and extract more features.On this basis,the above multi-attention mechanism is combined with a convolutional neural network to model and analyze the seven emotional categories of bullet screens.Testing from perspectives of model and dataset,experimental results can validate effectiveness of our approach.Finally,emotions of bullet screens are visualized to provide data supports for hot event controls and other fields.展开更多
Objective Through bibliometrics and visual analysis of the related studies on traditional Chinese medicine(TCM)treatment of immune thrombocytopenia(ITP),this study aims to sort out the overall research progress,hotspo...Objective Through bibliometrics and visual analysis of the related studies on traditional Chinese medicine(TCM)treatment of immune thrombocytopenia(ITP),this study aims to sort out the overall research progress,hotspots,and trends in this field,and provide reference for further research in ITP.Methods The articles on ITP treated by TCM were retrieved from China National Knowledge Infrastructure(CNKI),Wanfang Database,China Science and Technology Journal Database(VIP),Web of Science Core Collection(WOSCC),and PubMed.The retrieval time was from the establishment of the databases to July 31,2022.VOSviewer,CiteSpace,Carrot2,and Note-Express were used for data analysis of the articles in terms of their quantities,types,and journals,and for visualization of research hotspots,authors,institutions,and keywords.Results 1493 Chinese articles and 40 English articles were included.The articles in Chinese mainly focus on clinical trial research and clinical experience summary,while the English articles mainly focus on clinical trial research and animal research.The Chinese articles were published in 317 Chinese journals,while English articles were published in 29 English journals.Research hotspots include the clinical syndrome differentiation of ITP,the therapeutic effect of TCM compounds on ITP,and the mechanism of ITP treatment.Keyword analysis shows that there are many research achievements in integrated traditional Chinese and western medicine treatment,clinical research,famous doctors’experience,TCM treatment,cellular immunity,and humoral immunity.The authors with the most articles in Chinese and English are Professor CHEN Xinyi and Professor MA Rou,respectively,and the research institutions with the most articles are Dongzhimen Hospital of Beijing University of Chinese Medicine and Xiyuan Hospital of China Academy of Chinese Medical Sciences.Chinese herbs often used to treat ITP clinically include Xianhecao(Agrimoniae Herba),Nvzhenzi(Ligustri Lucidi Fructus),Mohanlian(Ecliptae Herba),Zhongjiefeng(Sarcandrae Herba),etc.,and the prescription usually used to treat ITP include Guipi Decoction(归脾汤),Xijiao Dihuang Decoction(犀角地黄汤),Bazhen Decoction(八珍汤),Erzhi Pill(二至丸),and Xiaochaihu De-coction(小柴胡汤).The main development trends toward retrospective study,TCM treatment mechanism,and data mining.展开更多
QTLNetworkR is an R package that aims to provide a user-friendly and platform-independent tool to visualize quantitative trait loci (QTL) mapping results. The graphical functions of the QTLNetworkR are based upon latt...QTLNetworkR is an R package that aims to provide a user-friendly and platform-independent tool to visualize quantitative trait loci (QTL) mapping results. The graphical functions of the QTLNetworkR are based upon lattice and grid packages, and the graphical user interface (GUI) of the QTLNetworkR is built upon RGtk2 and gWidgetsRGtk2 packages. Six functions are designed to help visualize marker interval, putative QTL, QTL-by- environment interactions, marker interval interactions, epistasis, and the predicted genetic architecture of complex traits. It is especially helpful in profiling results for multiple traits at multiple environments. The current version of QTLNetworkR is able to accept QTL mapping results from QTLNetwork, and it is ready for possible extensions to import results from some other QTL mapping software packages. In addition, we presented a QTL mapping result in rice (Oryza sativa) as an example to describe the features of QTLNetworkR.展开更多
基金National Natural Science Foundation of China(No.61562057)Gansu Science and Technology Plan Project(No.18JR3RA104)。
文摘With the development of short video industry,video and bullet screen have become important ways to spread public opinions.Public attitudes can be timely obtained through emotional analysis on bullet screen,which can also reduce difficulties in management of online public opinions.A convolutional neural network model based on multi-head attention is proposed to solve the problem of how to effectively model relations among words and identify key words in emotion classification tasks with short text contents and lack of complete context information.Firstly,encode word positions so that order information of input sequences can be used by the model.Secondly,use a multi-head attention mechanism to obtain semantic expressions in different subspaces,effectively capture internal relevance and enhance dependent relationships among words,as well as highlight emotional weights of key emotional words.Then a dilated convolution is used to increase the receptive field and extract more features.On this basis,the above multi-attention mechanism is combined with a convolutional neural network to model and analyze the seven emotional categories of bullet screens.Testing from perspectives of model and dataset,experimental results can validate effectiveness of our approach.Finally,emotions of bullet screens are visualized to provide data supports for hot event controls and other fields.
基金Jiangxi Traditional Chinese Medicine Administration Clinical Research Base Construction Project(Jiangxi TCM Science and Education Letter[2021]No.3)Jiangxi Traditional Chinese Medicine Young and Middle-aged Backbone Talents(First Batch)Training Program Project(Jiangxi TCM Science and Education Letter[2020]No.2)Jiangxi Traditional Chinese Medicine Administration Science and Technology Program Project(2021B050).
文摘Objective Through bibliometrics and visual analysis of the related studies on traditional Chinese medicine(TCM)treatment of immune thrombocytopenia(ITP),this study aims to sort out the overall research progress,hotspots,and trends in this field,and provide reference for further research in ITP.Methods The articles on ITP treated by TCM were retrieved from China National Knowledge Infrastructure(CNKI),Wanfang Database,China Science and Technology Journal Database(VIP),Web of Science Core Collection(WOSCC),and PubMed.The retrieval time was from the establishment of the databases to July 31,2022.VOSviewer,CiteSpace,Carrot2,and Note-Express were used for data analysis of the articles in terms of their quantities,types,and journals,and for visualization of research hotspots,authors,institutions,and keywords.Results 1493 Chinese articles and 40 English articles were included.The articles in Chinese mainly focus on clinical trial research and clinical experience summary,while the English articles mainly focus on clinical trial research and animal research.The Chinese articles were published in 317 Chinese journals,while English articles were published in 29 English journals.Research hotspots include the clinical syndrome differentiation of ITP,the therapeutic effect of TCM compounds on ITP,and the mechanism of ITP treatment.Keyword analysis shows that there are many research achievements in integrated traditional Chinese and western medicine treatment,clinical research,famous doctors’experience,TCM treatment,cellular immunity,and humoral immunity.The authors with the most articles in Chinese and English are Professor CHEN Xinyi and Professor MA Rou,respectively,and the research institutions with the most articles are Dongzhimen Hospital of Beijing University of Chinese Medicine and Xiyuan Hospital of China Academy of Chinese Medical Sciences.Chinese herbs often used to treat ITP clinically include Xianhecao(Agrimoniae Herba),Nvzhenzi(Ligustri Lucidi Fructus),Mohanlian(Ecliptae Herba),Zhongjiefeng(Sarcandrae Herba),etc.,and the prescription usually used to treat ITP include Guipi Decoction(归脾汤),Xijiao Dihuang Decoction(犀角地黄汤),Bazhen Decoction(八珍汤),Erzhi Pill(二至丸),and Xiaochaihu De-coction(小柴胡汤).The main development trends toward retrospective study,TCM treatment mechanism,and data mining.
基金Project supported by the National Basic Research Program (973) of China (No. 2008CB117002)the Ministry of Agriculture Public Benefit Research Foundation of China (No. 200803034)the National High-Tech R & D Program (863) of China (No. 2006AA10A102)
文摘QTLNetworkR is an R package that aims to provide a user-friendly and platform-independent tool to visualize quantitative trait loci (QTL) mapping results. The graphical functions of the QTLNetworkR are based upon lattice and grid packages, and the graphical user interface (GUI) of the QTLNetworkR is built upon RGtk2 and gWidgetsRGtk2 packages. Six functions are designed to help visualize marker interval, putative QTL, QTL-by- environment interactions, marker interval interactions, epistasis, and the predicted genetic architecture of complex traits. It is especially helpful in profiling results for multiple traits at multiple environments. The current version of QTLNetworkR is able to accept QTL mapping results from QTLNetwork, and it is ready for possible extensions to import results from some other QTL mapping software packages. In addition, we presented a QTL mapping result in rice (Oryza sativa) as an example to describe the features of QTLNetworkR.
