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.

A Large-Scale Group Decision Making Model Based on Trust Relationship and Social Network Updating

With the development of big data and social computing,large-scale group decisionmaking(LGDM)is nowmerging with social networks.Using social network analysis(SNA),this study proposes an LGDM consensus model that considers the trust relationship among decisionmakers(DMs).In the process of consensusmeasurement:the social network is constructed according to the social relationship among DMs,and the Louvain method is introduced to classify social networks to form subgroups.In this study,the weights of each decision maker and each subgroup are computed by comprehensive network weights and trust weights.In the process of consensus improvement:A feedback mechanism with four identification and two direction rules is designed to guide the consensus of the improvement process.Based on the trust relationship among DMs,the preferences are modified,and the corresponding social network is updated to accelerate the consensus.Compared with the previous research,the proposedmodel not only allows the subgroups to be reconstructed and updated during the adjustment process,but also improves the accuracy of the adjustment by the feedbackmechanism.Finally,an example analysis is conducted to verify the effectiveness and flexibility of the proposed method.Moreover,compared with previous studies,the superiority of the proposed method in solving the LGDM problem is highlighted.

Social Cost Analysis of Biological Control Technology for Crop Diseases and Insect Pests

With the rapid development of modern agriculture,the prevention and control of crop diseases and insect pests has become an important part to ensure the safety of agricultural production,the quality of agricultural products and the safety of agricultural ecological environment.Although the effect of traditional chemical prevention and control technology is remarkable,the health risks and environmental problems brought by it should not be ignored.As a green and environmentally friendly means of prevention and control,biological prevention and control technology has gradually become a hot research topic and a trend of agricultural production.This paper is intended to comprehensively evaluate the social costs of biological control technologies for crop diseases and pests,including the health risks reduced,environmental improvements,economic benefits,and barriers to promotion,and put forward corresponding policy recommendations.

Social Robot Detection Method with Improved Graph Neural Networks

Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social life.Existing social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social robots.This paper proposes a social robot detection method with the use of an improved neural network.First,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships effectively.Then,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the nodes.Next,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph features.Finally,social robots can be more accurately identified by combining user behavioral and relationship features.By carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,respectively.Compared with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two datasets.The results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.

Relationship between primary caregivers’social support function,anxiety,and depression after interventional therapy for acute myocardial infarction patients

BACKGROUND An acute myocardial infarction(AMI)is often treated with direct coronary intervention and requires home-based rehabilitation.Caregivers of patients with AMI need adequate social support to maintain high-quality care;however,their social support function is low,and relevant indicators for intervention must be identified.AIM To analyze the correlation between social support for primary caregivers,their anxiety,and depression,when caring for patients with AMI after interventional therapy.METHODS Using convenience sampling,we selected 300 primary caregivers of patients with AMI who had undergone interventional therapy.The Social Support Rating Scale(SSRS),Self-Rating Anxiety Scale(SAS),and Self-Rating Depression Scale(SDS)were used to assess the primary caregivers.A Pearson’s correlation analysis was used to analyze the correlations between the SSRS,SAS,and SDS,and a multiple logistic regression analysis was used to analyze the factors influencing the low social support function of primary caregivers.The receiver operating characteristic curve and area under the curve(AUC)were used to evaluate the predictive ability of the SAS and SDS for low social support function in primary caregivers.RESULTS Considering the norm among Chinese people,AMI caregivers’objective support,subjective support,support utilization,and SSRS scores were lower,while their SAS and SDS scores were higher.The SSRS scores of female caregivers were higher than those of the male caregivers(t=2.123,P=0.035).The Pearson correlation analysis showed that objective support,subjective support,support utilization,and SSRS total scores were significantly correlated with both SAS(r=-0.414,-0.460,-0.416,-0.535)and SDS scores(r=-0.463,-0.379,-0.349,-0.472).Among the 300 AMI caregivers,56 cases(18.67%)had a low level of support function(SSRS≤22 points).Logistic regression model analysis showed that SAS and SDS were independent risk factors for low social support function of AMI caregivers,regardless of adjustment for other variables(P<0.05).SAS and SDS predicted that the AUC of AMI caregivers with low support function was 0.84,sensitivity was 67.9 and 71.4,and specificity was 84.0 and 70.9,respectively.CONCLUSION The social support function of the primary caregiver of patients with AMI after interventional therapy was lower and negatively correlated with anxiety and depression in the primary caregiver.

Quantifying social costs of coal-fired power plant generation

Coal has been dominating the electricity supply in Indonesia,especially in long-term power generation from fossil energy.This dominance is due to lower production costs in coal-fired power plant generation.However,this low price is only based on monetary costs and ignores the social costs.Therefore,this study aims to quantify the social costs of coal-fired generation.Using QUERI-AirPacts modeling,the present study quantifies the social costs resulting from the Tenayan Raya coal-fired generation in Riau,Indonesia.It includes the levelized cost of electricity and health costs into the generation costs.After that,this study calculates the net present value,internal rate return,and project payback period.The study found that as much as$50.22/MWh was the levelized cost of electricity.While$15.978/MWh or$0.015978/kWh was the social cost that was not included in the generating cost.At the electricity production level of 1,380,171.69 MWh per year,there is an expected extra cost of$22,052,383.30 uncounted when externalities are included.For instance,the net present value(NPV)is lower and even negative when external costs are included(-$24,062,274.19)compared to$176,108,091.52 when externalities are not considered.The internal rate of return(IRR)is much higher when the social costs are not considered.The payback period is also shorter when the social costs are excluded than when the externalities are included.This global number indicates that the inclusion of external costs would impact NPV,IRR,and the payback period.This result implies that the government should internalize the external cost to stimulate the electricity producers to conduct cost-benefit analyses.The cost-benefit analysis mechanism would lead the producers to be more efficient.

Consensus model of social network group decision-making based on trust relationship among experts and expert reliability

Due to people’s increasing dependence on social networks,it is essential to develop a consensus model considering not only their own factors but also the interaction between people.Both external trust relationship among experts and the internal reliability of experts are important factors in decision-making.This paper focuses on improving the scientificity and effectiveness of decision-making and presents a consensus model combining trust relationship among experts and expert reliability in social network group decision-making(SN-GDM).A concept named matching degree is proposed to measure expert reliability.Meanwhile,linguistic information is applied to manage the imprecise and vague information.Matching degree is expressed by a 2-tuple linguistic model,and experts’preferences are measured by a probabilistic linguistic term set(PLTS).Subsequently,a hybrid weight is explored to weigh experts’importance in a group.Then a consensus measure is introduced and a feedback mechanism is developed to produce some personalized recommendations with higher group consensus.Finally,a comparative example is provided to prove the scientificity and effectiveness of the proposed consensus model.

Smart object recommendation based on topic learning and joint features in the social internet of things

With the extensive integration of the Internet,social networks and the internet of things,the social internet of things has increasingly become a significant research issue.In the social internet of things application scenario,one of the greatest challenges is how to accurately recommend or match smart objects for users with massive resources.Although a variety of recommendation algorithms have been employed in this field,they ignore the massive text resources in the social internet of things,which can effectively improve the effect of recommendation.In this paper,a smart object recommendation approach named object recommendation based on topic learning and joint features is proposed.The proposed approach extracts and calculates topics and service relevant features of texts related to smart objects and introduces the“thing-thing”relationship information in the internet of things to improve the effect of recommendation.Experiments show that the proposed approach enables higher accuracy compared to the existing recommendation methods.

An Estimation Method for Relationship Strength in Weighted Social Network Graphs

Previous works mainly focused on estimating direct relationship strength in social networks. If two users are not directly connected in a social network, there is no direct relationship. In order to estimate the relationship strength between two indirectly connected users as well as directly connected users, this paper proposes an estimation method for relationship strength in weighted social network graphs, which is based on the trust propagation strategy and the estimation of direct relationship strength. Our method considers the length of a relationship path, the number of relationship paths and the edge weights (direct relationship strength) along with a relationship path to estimate the strength of indirect relationship. Then it synthesizes the direct and indirect relationship strength to represent the strength of relationship between two users in social net- works. Thus our method can fully estimate the relationship strength between any two users in a social network no matter whether they are directly connected or not.

Dominance hierarchy and social relationships in a group of Captive black-and-white snub-nosed monkeys (Rhinopithecus bietl)

Different types of dominance hierarchies reflect different social relationships in primates. In this study, we clarified the hierarchy and social relationships in a one-male unit of captive Rhinopithecus bieti observed between August 1998 and March 1999. Mean frequency of agonistic behaviour among adult females was 0.13 interactions per hour. Adult females exhibited a linear hierarchy with a reversal of 10.9%, indicating an unstable relationship; therefore, R. bieti appears to be a relaxed/tolerant species. The lack of a relationship between the agonistic ratio of the adult male towards adult females and their ranks indicated that males did not show increased aggression towards low-ranking females. Differentiated female affiliative relationships were loosely formed in terms of the male, and to some extent influenced by female estrus, implying that relationships between the male and females is influenced by estrus and not rank alone. A positive correlation between the agonistic ratio of adult females and their ranks showed that the degree to which one female negatively impacted others decreased with reduction in rank. Similarly, a positive correlation between the agonistic ratio of females and differences in rank suggests that a female had fewer negative effects on closely ranked individuals than distantly ranked ones. These data indicate that rank may influence relationships between females. A steeper slope of regression between the agonistic ratio and inter-female rank differences indicated that the extent of the power difference in high-ranking females exerting negative effects on low-ranking ones was larger during the mating season than the birth season, suggesting that rank may influence the mating success of females.

Optimization for performance-based design under seismic demands, including social costs

Performance-based design in earthquake engineering is a structural optimization problem that has, as the objective, the determination of design parameters for the minimization of total costs, while at the same time satisfying minimum reliability levels for the specifi ed performance criteria. Total costs include those for construction and structural damage repairs, those associated with non-structural components and the social costs of economic losses, injuries and fatalities. This paper presents a general framework to approach this problem, using a numerical optimization strategy and incorporating the use of neural networks for the evaluation of dynamic responses and the reliability levels achieved for a given set of design parameters. The strategy is applied to an example of a three-story offi ce building. The results show the importance of considering the social costs, and the optimum failure probabilities when minimum reliability constraints are not taken into account.

Impact of social relationship on firms' sharing reward program

In order to make strategic decision on firms’ sharing reward program( SRP), a nested Stackelberg game is developed. The sharing behavior among users and the rewarding strategy of firms are modeled. The optimal sharing bonus is worked out and the impact of social relationships among customers is discussed. The results show that the higher the bonus,the more efforts the inductor is willing to make to persuade the inductee into buying. In addition,the firms should take the social relationship into consideration when setting the optimal sharing bonus. If the social relationship is weak,there is no need to adopt the SRP. Otherwise,there are two ways to reward the inductors. Also,the stronger the social relationship,the fewer the sharing bonuses that should be offered to the inductors,and the higher the expected profits. As a result,it is reasonable for the firms to implement SRPs on the social media where users are familiar with each other.

A Comparative Study of Quality of Family, Social Relationships and Type D Personality in Cardiovascular Patients and Non-Patients

This study aims to compare the quality of family and social relationships and Type D personality in cardiovascular patients with normal people. In this research, 300 individuals (n = 150 male, 150 female) are divided in two groups of patient (n = 150) and non-patients (n = 150) were selected as samples from the author’s offices (both private and his office in Mazandaran Heart Center). They attended in this study filling the questionnaires of “Pierce Quality relations” and “Personality Inventory (DS14)”. In order to analyze data, First observations were described by the help of descriptive statistics methods including tables, graphs, and indices of central tendency and distribution. Then, observations were described by inferential statistics methods such as univariate and multivariate analysis of variance and then were analyzed by SPSS. Out of the 300 participants, 108 patients (36%) had the mean age of 52 to 63 years old and 30 patients (10%) were 30 to 40 years old. This study showed that there is a significant difference between cardiovascular patients and control group in terms of quality of family and social relationships and Type D personality (P < 0.01). Cardiovascular patients have lower quality of family and social relationships, social support, as well as lower depth of relationships, and also higher relationship conflict than normal people. Also cardiovascular patients have higher type D personality than normal people (P < 0.01). In general, research findings indicate the importance of psychological factors associated with coronary artery disease.

Research on Coupling Relationship between Social Economy and Ecological Environment in Jinghe County of Aiby Lake Basin,Xinjiang

Based on the theory of sustainable development,using the theory and method of coupling relationship,the main city of Aiby Lake basin——Jinghe County in Xinjiang is selected. Based on the analyses of natural condition,population growth,land use type and ecological environment,the comprehensive evaluation index systems of socio-economic development level and eco-environment quality in Jinghe County are constructed. Using principal component analysis,a comprehensive evaluation of socio-economic development level and ecological environment quality in Jinghe County is conducted by combining with Excel. Their coupling relationship is studied,and quantitative coordination degree between social economy and ecological environment in Jinghe County is obtained. The results show that in recent 50 years,socio-economic development level in Jinghe County is rising,but the ecological environment quality is falling. Their coupling degree C changes during [- 1. 260, ＋ 0. 482],in other words,their coupling relationship is changing between ＂ reluctant coordination＂ and ＂ not coordination＂. After entering into the 21 stcentury,their coupling relationship is basically ＂ reluctant coordination＂. On this basis,the existing problems in the process of sustainable development in Jinghe County are analyzed,and the suggestions about promoting coordinated development between social economy and ecological environment are put forward.

The Relationship between Social Support and Burnout among ICU Nurses in Shanghai:A Cross-Sectional Study

Objective： The associations between social support and burnout were explored in ICU nurses of Shanghai. Methods： We performed a cross-sectional study of 356 ICU nurses by applying random cluster sampling. Data were collected using self-reported questionnaires under the instruction of trained investigators. Data on emotional exhaustion, depersonalisation and feelings of low personal accomplishment etc. were collected, calculated and analyzed. Results： The participants had a mean age of 26.96 years （SD 4.07）. The mean value （M） and stand- ard deviation （SD） of emotional exhaustion was M=31.85, SD=8.38, those of depersonalisation was M= 11.69, SD= 5.54 and those of feelings of low personal accomplishment was M= 19. 79, SD = 7.02. The high degree of emotional exhaustion （EE）, depersonalisation （DP）, and lack of personal accomplishment （PA） were revealed to be 76.4%, 39.6%, and 94.9%, respectively. The major influencing factors of emotional exhaustion included support from co-workers（b=0. 343, t = 1.98, P=0. 049）, taking leave（b=-1. 182, t=-3. 747, P=0. 001）, requisition of work（b=-l. 41, t=-2. 369, P=0. 018）, and supervisor support（b=-0. 524, t=-3. 926, P=0. 001）. The major influencing factors of depersonalisation were support from the supervisor（b=-0. 333, t=-4. 146, P=0.001）, age（b=-0. 89, t=-2. 272, P= 0. 024） and requisition of work（b=-0. 148, t=-2. 124, P=0. 034）. There was a positive co-relationship between personal accomplishment and supervisor support. Conclusions： Supervisor support, age, and requisition of work were the major influencing factors of depersonalisation. In addition, supervisor support plays an important role in low personal accomplishment. Further research should focus on supervisor support, co-worker support, time on leave, and requisition of work associated with emotional exhaustion.

Enterprise innovation, corporate social responsibility and their interactive relationship: A review

Under the new normal economic growth, lack of motivation, structural imbalances in the economy, the shortage of resources, resource utilization inefficiency, environmental damage and other issues have become increasingly prominent, enterprises as the carrier of economy is one of the root of the problem. Research on enterprise innovation and corporate social responsibility issues, it is conducive to the development of enterprise itself and the transformation of Chinese economy. This paper reviewed the research status of relationships between innovation and corporate social responsibility, through comb the aspects of the definitions and evolution of enterprise innovation and social responsibility, also include both the relationship and the new way(responsible innovation) of combination of them, we found the presence of index system is not perfect, and lack of in-depth comprehensive study and opportunities for future research is prospected.

Open pit limit optimization considering economic profit,ecological costs and social benefits

Pit limit design has,up to date,focused mainly on maximization of economic profit alone,with environmental and social issues largely ignored.This paper focuses on incorporating both environmental and social issues in the pit limit design process and provides an approach to pit limit optimization that is in compliance with sustainable development.The case study demonstrates that ecological costs have a substantial down-sizing effect and social benefits have a substantial up-sizing effect on the optimal pit limit.When the ecological costs are factored in,the optimal pit limit is 37.5%smaller than the economically optimal pit limit.However,when the social benefits are factored in,the optimal pit limit is 48.3%larger than the economically optimal one.The overall optimal pit limit,with the economic profit,ecological costs and social benefits simultaneously considered,is a result of balancing conflicting goals of maximizing economic profit,minimizing ecological cost,and maximizing social benefit.

Health Hot Spots: Mapping Hospital Costs and Social Determinants of Health

Accountable care organizations (ACOs) and hospitals are facing additional requirements and financial rewards for improving population health. Therefore, ACOs and hospitals will need tools to understand the relationship between their patients and social determinants and health. We demonstrate the use of hot spotting for identifying geographical sources of high hospital costs and examining links between social determinants of health and these high-cost areas, known as hot spots. In 2012, using hospital data, we generated maps of inpatient costs from 2011 throughout New Haven and within an example neighborhood, Dixwell. We defined hot spots as addresses where costs were in the top 25%. We also overlaid data on concerns and assets in the community. Finally, we calculated the number of concerns and assets that fall within the 250 and 500 ft radii of the defined hot spots. We found that 34 addresses in Dixwell accounted for 70% of total costs for Dixwell. Hot spotting is a straightforward, approachable, and easily understood method for ACOs and hospitals to begin to address population health.

Extension of Switching Costs Antecedents Based on Customers＇ Social Ties

The effects of customers' social ties on switching costs have recently attracted researchers' attention.This study formally included customers' social ties as a new antecedent to supplement those elucidated by Burnham in 2003.Through empirical research,this study successfully verified the reliability and validity of items created to measure social ties,and it demonstrated the facilitating effects of social ties as an antecedent on customers' procedural and relational switching costs.Finally,the study lists managerial implications aimed at retaining customers through knowledge of this added antecedent.

An Exploratory Study into Social Cost Considerations in Ghanaian Construction Industry

Construction causative nuisances, inconveniences, interferences and disruptions to the routine economic and social life patterns of adjacent or neighboring communities are referred to as social cost. This study explores the understanding and level of consideration of social cost by construction professionals in Ghana. Relevant literature sources are reviewed to define, rationalize and classify social cost. The study used the survey approach with a set of questionnaires addressed to construction contractors and professionals to gather the data. It was realized that not much consideration is given to social cost at the tender stage of the construction process. The five factors hindering social cost inclusion in tendering are “difficulty in allocating social costs”, “governmental interferences”, “lack of historical data”, “lack of appreciation of social costs” and “low stakeholder agitation”. The paper advocated for integration of social cost into the tendering process. The study will serve as a foundation to design a social cost assessment system at the pre-contract stage.