An Emotion Analysis Method Using Multi-Channel Convolution Neural Network in Social Networks

As an interdisciplinary comprehensive subject involving multidisciplinary knowledge,emotional analysis has become a hot topic in psychology,health medicine and computer science.It has a high comprehensive and practical application value.Emotion research based on the social network is a relatively new topic in the field of psychology and medical health research.The text emotion analysis of college students also has an important research significance for the emotional state of students at a certain time or a certain period,so as to understand their normal state,abnormal state and the reason of state change from the information they wrote.In view of the fact that convolutional neural network cannot make full use of the unique emotional information in sentences,and the need to label a large number of highquality training sets for emotional analysis to improve the accuracy of the model,an emotional analysismodel using the emotional dictionary andmultichannel convolutional neural network is proposed in this paper.Firstly,the input matrix of emotion dictionary is constructed according to the emotion information,and the different feature information of sentences is combined to form different network input channels,so that the model can learn the emotion information of input sentences from various feature representations in the training process.Then,the loss function is reconstructed to realize the semi supervised learning of the network.Finally,experiments are carried on COAE 2014 and self-built data sets.The proposed model can not only extract more semantic information in emotional text,but also learn the hidden emotional information in emotional text.The experimental results show that the proposed emotion analysis model can achieve a better classification performance.Compared with the best benchmark model gram-CNN,the F1 value can be increased by 0.026 in the self-built data set,and it can be increased by 0.032 in the COAE 2014 data set.

Construction of Short-Block Nonbinary LDPC Codes Based on Cyclic Codes

In this paper, we focus on shortblock nonbinary LDPC(NB-LDPC) codes based on cyclic codes. Based on Tanner graphs' isomorphism, we present an efficient search algorithm for finding non-isomorphic binary cyclic LDPC codes. Notice that the parity-check matrix H of the resulting code is square and not of full rank, and its row weight and column weight are the same. By replacing the ones in the same column of H with a nonzero element of fi nite fi elds GF(q), a class of NB-LDPC codes over GF(q) is obtained. Numerical results show that the constructed codes perform well over the AWGN channel and have fast decoding convergence. Therefore, the proposed NB-LDPC codes provide a promising coding scheme for low-latency and high-reliability communications.

Interlayer-decoupled BiOX (X=Cl, Br, and I) sheets for photocatalytic water splitting:a computational study

In this work, we comprehensively study the electronic and photocatalytic properties of single-layer and multilayer bismuth oxyhalides Bi OX(X=Cl, Br, and I) sheets by means of extensive density functional theory, which have been successfully synthesized in the previous experimental studies. Our computational simulations show that single-layer Bi OX sheets possess indirect band gap, suitable band edge alignments, and pronounced optical properties, suggesting that they can be utilized as photocatalysts for splitting H_(2)O into H_(2) and O_(2) from theoretical aspects. In the case of multilayer Bi OX sheets, some primary physical properties determined the photocatalytic performance are rather robust, almost independent of the layer number. According to these calculated results, we are optimistic that Bi OX sheets, especially for single-layer Bi OI, have great chances to be used for photocatalytic water splitting.