Predicting Users’ Latent Suicidal Risk in Social Media: An Ensemble Model Based on Social Network Relationships

Suicide has become a critical concern,necessitating the development of effective preventative strategies.Social media platforms offer a valuable resource for identifying signs of suicidal ideation.Despite progress in detecting suicidal ideation on social media,accurately identifying individuals who express suicidal thoughts less openly or infrequently poses a significant challenge.To tackle this,we have developed a dataset focused on Chinese suicide narratives from Weibo’s Tree Hole feature and introduced an ensemble model named Text Convolutional Neural Network based on Social Network relationships(TCNN-SN).This model enhances predictive performance by leveraging social network relationship features and applying correction factors within a weighted linear fusion framework.It is specifically designed to identify key individuals who can help uncover hidden suicidal users and clusters.Our model,assessed using the bespoke dataset and benchmarked against alternative classification approaches,demonstrates superior accuracy,F1-score and AUC metrics,achieving 88.57%,88.75%and 94.25%,respectively,outperforming traditional TextCNN models by 12.18%,10.84%and 10.85%.We assert that our methodology offers a significant advancement in the predictive identification of individuals at risk,thereby contributing to the prevention and reduction of suicide incidences.

Meteorological satellite stakeholder relationship network based on social network analysis

The meteorological satellite service range is extensive,and science and technology and related industries have become beneficiaries of it.The complex meteorological satellite stakeholder relationship warrants quantitative evaluation.This study investigates the meteorological satellite stakeholder relationship network to provide a new research perspective for meteorological satellites in the field of management.For literature analysis,16 meteorological satellite stakeholders are identified through keyword screening,classified,and coded.A meteorological satellite stakeholder relationship network model is then constructed through social network analysis(SNA).Ego,local,and overall networks are analyzed from three perspectives to measure the network principle and to form a relationship network coordination degree evaluation system.The improved analytic hierarchy process(AHP)-fuzzy comprehensive evaluation method is then used to determine index weights and evaluate the relationship network coordination process design comprehensively.In empirical analysis,data for the meteorological satellite Fengyun-4 are obtained through questionnaire survey and literature analysis.Ucinet6 is used to generate relationship networks and analyze various stakeholder roles and status,stakeholder relationship network coordination degree,and evaluation results.The results demonstrate that the competent meteorological satellite department,the meteorological administration,the National Meteorological Centre,and the government are in the center of the Fengyun-4 stakeholder relationship network,with coordination degree in an“average”state.Thus,establishing a stakeholder coordination mechanism may strengthen connection and promote the development of meteorological undertakings.

The application of neural networks to comprehensive prediction by seismology prediction method

BP neural networks is used to mid-term earthquake prediction in this paper. Some usual prediction parameters of seismology are used as the import units of neural networks. And the export units of neural networks is called as the character parameter W_0 describing enhancement of seismicity. We applied this method to space scanning of North China. The result shows that the mid-term anomalous zone of W_0-value usually appeared obviously around the future epicenter 1~3 years before earthquake. It is effective to mid-term prediction.

ARTIFICIAL NEURAL NETWORK MODEL OF CONSTITUTIVE RELATIONSHIP FOR 2A70 ALUMINUM ALLOY

The hat deformation behavior of 2A70 aluminum alloy was investigated by means of isothermal compression tests performed on a Gleeble-1500 thermal simulator over a wide range of temperatures 360-480℃ with strain rates of 0.01-1s^-1 and the largest deformation of 60%, and the true stress of the material was obtained under the above-mentioned conditions. The experimental results shows that 2A70 aluminum alloy is a kind of aluminum alloy with the property of dynamic recovery; its flow stress declines with the increase of temperature, while its flow stress increases with the increase of strain rates. On the basis of experiments, the constitutive relationship of the 2A70 aluminum alloy was constructed using a BP artificial neural network. Comparison of the predicted values with the experimental data shows that the relative error of the trained model is less than ±3% for the sampled data while it is less than ±6% for the nonsampled data. It is evident that the model constructed by BP ANN can accurately predict the flow stress of the 2A70 alloy.

Bibliometric analysis of subject trends and knowledge structures of gut microbiota

BACKGROUND Gut microbiota is an emerging field of research,with related research having breakthrough development in the past 15 years.Bibliometric analysis can be applied to analyze the evolutionary trends and emerging hotspots in this field.AIM To study the subject trends and knowledge structures of gut microbiota related research fields from 2004 to 2018.METHODS The literature data on gut microbiota were identified and downloaded from the PubMed database.Through biclustering analysis,strategic diagrams,and social network analysis diagrams,the main trend and knowledge structure of research fields concerning gut microbiota were analyzed to obtain and compare the research hotspots in each period.RESULTS According to the strategic coordinates and social relationship network map,Clostridium Infections/microbiology,Clostridium Infections/therapy,RNA,Ribosomal,16S/genetics,Microbiota/genetics,Microbiota/immunology,Dysbiosis/immunology,Infla-mmation/immunology,Fecal Microbiota Transplantation/methods,Fecal Microbiota Transplantation can be used as an emerging research hotspot in the past 5 years(2014-2018).CONCLUSION Some subjects were not yet fully studied according to the strategic coordinates;and the emerging hotspots in the social network map can be considered as directions of future research.

Research on community detection algorithm based on site topic similarity and topology

Considering the deviation in content of community detection resulting from the tow accuracy of resource relevance, an algorithm based on the topology of sites and the similarity between their topics is proposed. With topic content factors fully considered, this algorithm can search for topically similar site clusters on the premise of inter-site topology. The experimental results show that the algorithm can generate a more accurate result of detection in the real network.

A new group contribution-based method for estimation of flash point temperature of alkanes

Flash point is a primary property used to determine the fire and explosion hazards of a liquid. New group contribution-based models were presented for estimation of the flash point of alkanes by the use of multiple linear regression(MLR)and artificial neural network(ANN). This simple linear model shows a low average relative deviation(AARD) of 2.8% for a data set including 50(40 for training set and 10 for validation set) flash points. Furthermore, the predictive ability of the model was evaluated using LOO cross validation. The results demonstrate ANN model is clearly superior both in fitness and in prediction performance.ANN model has only the average absolute deviation of 2.9 K and the average relative deviation of 0.72%.

Meta-Path-Based Search and Mining in Heterogeneous Information Networks

Information networks that can be extracted from many domains are widely studied recently. Different functions for mining these networks are proposed and developed, such as ranking, community detection, and link prediction. Most existing network studies are on homogeneous networks, where nodes and links are assumed from one single type. In reality, however, heterogeneous information networks can better model the real-world systems, which are typically semi-structured and typed, following a network schema. In order to mine these heterogeneous information networks directly, we propose to explore the meta structure of the information network, i.e., the network schema. The concepts of meta-paths are proposed to systematically capture numerous semantic relationships across multiple types of objects, which are defined as a path over the graph of network schema. Meta-paths can provide guidance for search and mining of the network and help analyze and understand the semantic meaning of the objects and relations in the network. Under this framework, similarity search and other mining tasks such as relationship prediction and clustering can be addressed by systematic exploration of the network meta structure. Moreover, with user＇s guidance or feedback, we can select the best meta-path or their weighted combination for a specific mining task.

StarIn:An Approach to Predict the Popularity of GitHub Repository

The popularity of repository in GitHub is an important indicator to evaluate its quality.Exploring the trend of popularity is a crucial guideline to study its development potential.Herein,StarIn,a stargazer-influence based approach is proposed to predict the popularity of GitHub repository.Using the followers in GitHub as a basic dataset,stargazer-following based network was established.The indicator,stargazer influence,was measured from three aspects of basic influence,network dynamic influence and network static influence.Experiments was conducted,and the correlation of StarIn was analyzed with the popularity of repository from the perspective of six characteristics.The experimental evaluation provides an interesting approach to predict the popularity of repositories in GitHub from a new perspective.StarIn achieves an excellent performance of predicting the popularity of repositories with a high accurate rate under two different classifiers.