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
In this paper, considering the different elastic properties in the attached head and the free head, we propose a physical model, in which the free head undergoes a diffusive search in an entropic spring potential form...In this paper, considering the different elastic properties in the attached head and the free head, we propose a physical model, in which the free head undergoes a diffusive search in an entropic spring potential formed by undocking the neck linker, and there are asymmetric conformational changes in the attached head formed by docking the neck linker to support the load force and bias the diffusive search to the forward direction. By performing the thermodynamic analysis, we obtain the free energy difference between forward and backward binding sites. And using the Fokker-Planck equation with two absorbing boundaries, we obtain the dependence of the ratio of forward to backward steps on the backward force. Also, within the Michaelis-Menten model, we investigate the dependence of the velocity-load relationship on the effective length of the junction between the two heads. The results show that our model can provide a physical understanding for the processive movement of kinesin.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.
文摘In this paper, considering the different elastic properties in the attached head and the free head, we propose a physical model, in which the free head undergoes a diffusive search in an entropic spring potential formed by undocking the neck linker, and there are asymmetric conformational changes in the attached head formed by docking the neck linker to support the load force and bias the diffusive search to the forward direction. By performing the thermodynamic analysis, we obtain the free energy difference between forward and backward binding sites. And using the Fokker-Planck equation with two absorbing boundaries, we obtain the dependence of the ratio of forward to backward steps on the backward force. Also, within the Michaelis-Menten model, we investigate the dependence of the velocity-load relationship on the effective length of the junction between the two heads. The results show that our model can provide a physical understanding for the processive movement of kinesin.
