Public Sentiment Analysis of Social Security Emergencies Based on Feature Fusion Model of BERT and TextLevelGCN

At present, the emotion classification method of Weibo public opinions based on graph neural network cannot solve the polysemy problem well, and the scale of global graph with fixed weight is too large. This paper proposes a feature fusion network model Bert-TextLevelGCN based on BERT pre-training and improved TextGCN. On the one hand, Bert is introduced to obtain the initial vector input of graph neural network containing rich semantic features. On the other hand, the global graph connection window of traditional TextGCN is reduced to the text level, and the message propagation mechanism of global sharing is applied. Finally, the output vector of BERT and TextLevelGCN is fused by interpolation update method, and a more robust mapping of positive and negative sentiment classification of public opinion text of “Tangshan Barbecue Restaurant beating people” is obtained. In the context of the national anti-gang campaign, it is of great significance to accurately and efficiently analyze the emotional characteristics of public opinion in sudden social violence events with bad social impact, which is of great significance to improve the government’s public opinion warning and response ability to public opinion in sudden social security events. .

An Analysis of the Evolution of Online Public Opinion on Public Health Emergencies by Combining CNN-BiLSTM + Attention and LDA

In this paper, the Foxconn epidemic event in Zhengzhou was taken as an example to analyze the evolution of online public opinion on public health emergencies. In order to improve the performance of online public opinion analysis, based on the life cycle theory and LDA theory, the emotional changes of Internet users in four stages of the Foxconn incident centered on the evolution of inscription were divided. The emotions of netizen speech at different stages are analyzed based on CNN-BiLSTM + Attention model, which uses Convolutional Neural Network (CNN) to extract local features. Bi-directional Long Short-Term Memory (BiLSTM) is used to efficiently extract contextual semantic features and long distance dependencies, and then combined with attention mechanism to add emotional features. Finally, Softmax classifier realizes text emotion prediction. The experimental results show that: compared with TextCNN, BiLSTM, BiLSTM + Attenion, CNN-BiLSTM model, the emotion classification model has better effects in the accuracy rate, accuracy rate, recall rate and F value. By analyzing the emotional distribution and evolution trend of public opinion under “text topic”, the paper accurately deconstructs the development characteristics of public opinion in public health emergencies, in order to provide reference for relevant departments to deal with public opinion in public health emergencies. .

Microbiome and ileum transcriptome revealed the boosting effects of selenium yeast on egg production in aged laying hens

The declines in laying performance during the late productionperiod have adverse effects on the length of theproduction cycle. Improving the nutrition of laying hens is a crucialmeasure to reverse this declination. Thisstudy investigatedthe effect of seleniumyeast (SY)on egg production, ileal gene expressionandmicrobiota, aswell as elucidating their associations in aged laying hens. A total of 375 Jinghong laying hens at 76weeks oldwere randomly assigned into 5 dietary treatments, which included a selenium-deficient basal diet based oncorn-soybean meal, and dietary supplementation of SY at 0.15, 0.30 and 0.45 mg/kg, and sodium selenite at0.45mg/kg.The results showed that SYamelioratedthe depressionin aged layingperformance inthe 0.30mg/kg group (P < 0.01). Selenium yeast significantly increased ileum selenium concentration (P < 0.05), and SYgroups had higher seleniumdeposition efficiency than the sodiumselenite group. Functional enrichment andShort Time-series Expression Miner (STEM) analysis indicated that SY activated metabolic progress (e.g.,glycerolipidmetabolism, glycerophospholipidmetabolism, andfattyacidmetabolism),immune responseandoxidative stress response. Four hub genes including thioredoxin reductase 1 (TXNRD1), dihydrolipoamidedehydrogenase (DLD), integrin linked kinase (ILK) and leucine zipper tumor suppressor 2 (LZTS2) wereinvolved in intestinal metabolismwhich was closely associated with selenium deposition/status. Moreover,the relative abundance of Veillonella, Turicibacter and Lactobacillus was significantly increased, but the relativeabundance of Stenotrophomonas was significantly decreased by SY supplementation. Multi-omics dataintegration and Canonical correspondence analysis (CCA) showed that both the ileumselenium content andthe laying rate were highly correlated with pathways and bacteria enriched in metabolism and immuneresponse. Meanwhile, the “switched on” gene prostate stem cell antigen (PSCA) had a positive relationshipwith Veillonella and a negative relationship with the opportunistic pathogens Stenotrophomonas. Overall, ourstudy offered insight for the further exploration of the role of SY on boosting egg production and balancingileum intestinal flora in aged laying hens.

Ultra-low detection delay drift caused by the temperature variation in a Si-avalanche-photodiode-based single-photon detector

We report a method to reduce the detection delay temperature drift for a single-photon detector based on the avalanche photodiode(SPAD). Both the SPAD and the comparator were temperature stabilized, resulting in an ultra-low temperature drift at 0.01 ps/°C. A stable time deviation as 0.15 ps over 1000 s was realized, while the ambient temperature fluctuated rapidly from 24°C to 44°C. To the best of our knowledge, this is the first report on the ultra-stable delay SPAD detector in the case of rapid increase or decrease of ambient temperature. It is helpful to improve the stability of onboard detectors for optical laser time transfer between ground and space.