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.

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.

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.

Wear Fault Diagnosis of Machinery Based on Neural Networks and Gray Relationships

In this paper, the regular characteristic of -wear particles related to fault type of machines based on condition monitoring of reciprocal machinery is discussed. The typical -wear particles spectrum is established according to the equipment structure , friction and wear rule and the characteristic of 'wear particles; The identification technology of wear particles is proposed based on neural networks and a gray relationship ; an intelligent wear particles identification system is designed. The diagnosis example shows that this system can promote the accuracy and the speed of wear particles identification.

Self-Organized Detection of Relationships in a Network

Multistate operations within a network result in high-dimensional, multivariate temporal data, and are useful for systems, which monitor access to network entities like resources, objects, etc. Efficient self organization of such multi-state network operations stored in databases with respect to relationships amongst users or between a user and a data object is an important and a challenging problem. In this work, a layer is proposed where discovered relationship patterns amongst users are classified as clusters. This information along with attributes of involved users is used to monitor and extract existing and growing relationships. The correlation is used to help generate alerts in advance due to internal user-object interactions or collaboration of internal as well as external entities. Using an experimental setup, the evolving relationships are monitored, and clustered in the database.

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.

On Exploiting Temporal, Social, and Geographical Relationships for Data Forwarding in Delay Tolerant Networks

Because of unpredictable node mobility and absence of global information in Delay Tolerant Networks (DTNs), effective data forwarding has become a significant challenge in such network. Currently, most of existing data forwarding mechanisms select nodes with high cumulative contact capability as forwarders. However, for the heterogeneity of the transient node contact patterns, these selection approaches may not be the best relay choices within a short time period. This paper proposes an appropriate data forwarding mechanism, which combines time, location, and social characteristics into one coordinate system, to improve the performance of data forwarding in DTNs. The Temporal-Social Relationship and the Temporal-Geographical Relationship reveal the implied connection information among these three factors. This mechanism is formulated and verified in the experimental studies of realistic DTN traces. The empirical results show that our proposed mechanism can achieve better performance compared to the existing schemes with similar forwarding costs (e.g. end-to-end delay and delivery success ratio).

学习型社区赋能教育强国建设——基于在线学习者关系网络分析视角

学习型社区建设有助于加快教育强国落地,社区中在线学习者的各种协作互动行为,促进了学习者关系网络的生成。对该网络进行深入分析,可以挖掘其中蕴含的社区学习的本质特征。该研究提出从社区发现角度对学习者关系网络进行分析,首先设计基于图卷积网络和非负矩阵分解,并集成学习者关系网络信息和文本内容信息的新型学习型社区发现方法,提出四个社区特征度量指标,在真实的学习者关系网络中进行应用分析。结果表明,所提出的分析方法能有效挖掘学习者关系网络存在的学习兴趣主题社区,还可以对社区整体和社区成员个体进行特征分析,并且分析结果可为引导学习者的在线交互协作行为提供决策支持。最后,形成“构建可视化学习型社区—开展社区之间知识分享—促进各社区的互动合作—指标反馈下的反思迭代”的学习型社区赋能策略。通过策略赋能学习型社区高质量发展,以社区新质生产力组合助推教育强国建设。

中国数字经济空间动态演进的区域现状

数字经济已成为引领我国经济一体化高质量发展的主要驱动力,立足于国家整体经济及区域经济稳步协调发展的战略。文章基于中国2013—2020年省级数据,运用主成分分析法对中国数字经济进行测度,并运用社会网络分析及核密度等方法对我国数字经济动态演化的空间关联及区域差异进行研究。研究发现:(1)2013—2020年我国数字经济发展整体网络密度稳步提升但依旧处于低水平。(2)中国各省份数字经济发展两极分化,东部与西北、东北等边缘地区存在“数字经济鸿沟”,加之整体关联水平低,分化严重,发达地区对边缘地区的辐射效应较低,差距可能愈发扩大。(3)将其划分为四个板块,发现存在“弱关联”板块,板块间溢出关系及关联度差异悬殊,进一步研究各省份数字经济发展的“中间人”作用,发现各省份承担角色更是“极化”严重。研究结果可为我国持续深化数字经济建设,推动经济协调、稳定、高质量发展提供参考。

面向新质生产力发展需求的国家水网建设关键内容及研究展望

为推动国家水网建设稳步迈入新质生产力发展的新征程,在理解水利新质生产力内涵及发展需求的基础上,从高科技、高效能、高质量、绿色4个维度出发,系统梳理国家水网建设需要把握的关键内容,分析有代表性的研究实例,并在此基础上进一步对国家水网未来研究进行展望,包括研发国家水网模拟器大科学装置、物理水网和虚拟水网协同建设、支撑人与自然和谐共生的现代化建设、科学处理人水关系4个方面,以期为面向新质生产力发展的国家水网建设提供参考。

数字人文视域下20世纪留美作曲家社会网络关系分析

20世纪留美作曲家群体为近现代以来中国音乐的发展做出了不可替代的贡献。文章从数字人文角度出发,梳理多方数据来源,利用社会网络分析软件Ucinet构建20世纪留美作曲家群体社会关系网络,计算网络特征指标,并从师承关系、校友关系、同乡关系三个方面剖析了留美作曲家社会网络关系,具有多重发现,为中国近代音乐史、留学史以及作曲家群体研究提供了新的视角与方法。

非正式关系网络参与社区科普的实践路径

党的二十大报告指出,要增强城乡社区群众自我管理、自我服务、自我教育、自我监督的实效。科学理性认知氛围是场域内危机事件处理的关键要素。社区科普有利于夯实社区治理基础应对突发事件、构建学习型社区、促进文明社会形成、推动全过程民主的基层实现。非正式关系网络参与社区科普能够提升社区科普有效供给率、促进社区管理向社区治理转化、调动社区知识精英力量参与社区治理、深度嵌入居民生活开展科普宣传。其实践路径主要包括整合科普主体、推动组织赋权、构建协商制度、搭建数字平台等。但非正式关系网络参与社区科普也面临着可持续性、弱结构与强任务的不匹配以及行政威权排斥专业权威等问题。因此,要更好地推进非正式关系网络社区科普实践的正面建构。

合作网络嵌入对企业技术创新绩效的影响——基于知识网络凝聚性视角

基于网络嵌入理论和知识基础理论,利用我国电子信息产业114家企业的面板数据,实证分析了合作网络嵌入对企业技术创新绩效的影响,并进一步探究企业知识网络的凝聚水平对该过程的调节作用。结果表明,合作网络中的关系嵌入对企业技术创新绩效具有正向影响,结构嵌入对技术创新绩效具有负向影响;企业知识网络的全局凝聚性在结构嵌入对企业技术创新绩效的影响中具有正向调节作用,在关系嵌入对技术创新绩效的影响中不具有调节作用;企业知识网络局部凝聚水平在关系嵌入和结构嵌入对技术创新绩效的影响中均具有正向调节作用;合作网络嵌入对东部地区企业的技术创新绩效影响更为显著。

共享单车与公共交通多元关系分类及阈值研究

为准确评估共享单车和公共交通之间的复杂时空关系,根据替代或补充关系的具体成因类型,结合共享单车出行起讫点的分布情况,定义共享单车与公共交通多元关系;其次,考虑公共汽电车与轨道交通的差异性,提出一种基于弱监督全连接神经网络的共享单车与公共交通多元关系的分类模型,并根据共享单车轨迹数据,计算不同关系分类和交通方式下的公共交通可达范围、共享单车骑行时长及步行接驳距离边界阈值。结果表明:共享单车与公共交通的多元关系可分为接驳补充、空白补充、替代关系1和替代关系2。其中,共享单车与公共汽电车多元关系的三参数划分阈值分别为329.75 m、5.07 min和182.93 m,与轨道交通多元关系的划分阈值分别为816.96 m、10.27 min和653.91 m。共享单车与公共汽电车以替代关系1为主,占总行程的54.98%;共享单车与轨道交通以空白补充关系为主,占总行程的48.90%。共享单车与公共汽电车关系主要为多元替代与接驳补充,与轨道交通主要为多元补充与替代关系2。共享单车与公共汽电车的关系相比于轨道交通会更为复杂。本文可为促进共享单车与公共交通在各自优势距离上的协同发展提供支撑。

知识网络视角下科学、技术、产业间创新驱动关系识别方法研究

开展科学、技术、产业之间创新驱动关系研究,对于实现科学发现、技术创新与产业的深度有效融合与发展具有重要意义。本文从知识网络视角展开科学、技术、产业间创新驱动关系识别方法研究。首先,通过构建时效知识网络,利用社区网络结构熵来表征知识网络结构特征;其次,利用网络结构特征信息间的传递熵探究创新过程中科学、技术、产业三个系统相互驱动的关系;再其次,采用互信息探测主要驱动关系下知识传递路径的变化特点;最后,以再生医学(干细胞)领域作为实证对象,实证研究发现不同时间阶段,科学、技术、产业之间的相互驱动关系会发生转变,三者知识传递路径上知识内容前后继承关系也不同,科学驱动技术过程中的知识传递路径继承性特征持续增强,而技术驱动科学过程中的知识传递路径继承性呈现不稳定、非连续性特征。此外,通过多种方式论证了本文方法的科学有效性,可以用于其他创新领域科学、技术、产业间创新驱动关系的识别。

商会关系、声誉机制与代理成本

以中国证券市场2004—2021年A股上市公司为研究对象,研究企业家(董事长或总经理)商会关系资本与企业代理成本之间的关系,并进一步考察企业家个人声誉机制对上述关系的潜在影响。研究结果表明:企业家商会关系能够降低企业代理成本,且企业家商会任职层级越高、任职种类越多,抑制作用越显著;当企业家拥有人大代表或政协委员的政治身份以及兼任其他上市公司董事的社会身份等个人声誉时,商会关系对企业代理成本的抑制作用较弱;渠道检验发现,激励机制和监督机制是企业家商会关系作用于企业代理成本的重要渠道;进一步分析发现,企业家行业协会关系、国家及省级商会关系对代理成本的抑制作用更加明显,在非国有企业中企业家商会关系对代理成本的抑制作用更加明显。研究结论丰富和拓展了关系社会资本的微观经济后果及作用机制,为深入理解商会关系文化对微观企业决策行为的作用机制提供了初步的理论分析框架和经验证据。

融合社交关系和时序特征的图神经网络推荐模型

为解决推荐模型中的用户信息缺失和用户动态偏好问题,满足用户个性化需求,提出一种融合社交关系和时序特征的图神经网络推荐模型。该模型先构建社交关系图,并通过注意力机制得到基于社交关系的用户潜在特征;再构建用户-项目交互图,利用门控循环单元和注意力机制捕获交互信息,分别获得用户的时序特征和项目特征;最后将用户潜在特征与时序特征融合得到新的用户特征,并将其与项目特征进行融合,经过多层感知机得到最终推荐结果。在不同数据集上进行实验,结果表明,该模型能更好地处理用户信息缺失和用户动态偏好问题,进而提升推荐性能。相较于经典的图神经网络推荐模型,该模型的精确率和归一化折损累计增益比分别提高了4.0%和4.1%。

融合用户社交关系的自适应图卷积推荐算法

为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法(adaptive graph convolutional recommendation algorithm integrating user social relationships,AGCRSR)。首先,模型在嵌入层使用映射矩阵将初始特征向量转换为自适应嵌入;其次,引入注意力机制聚合不同方面的用户嵌入,通过图卷积网络来线性学习用户和项目的潜在表示;最后,通过自适应模块聚合用户表示并利用内积函数预测用户对项目的最终推荐结果。在数据集LastFM和Ciao上与其他基线算法进行了对比实验,实验结果表明AGCRSR的推荐效果较其他算法有显著提升。

基于STE-TCN的中短期电力负荷预测

目的 针对传统电力负荷预测模型对长序列预测精度低的问题,提出一种结合跳级卷积连接与时间编码网络的新型时序卷积神经网络(TCN)模型——STE-TCN模型。方法 首先对TCN模型加入跨周期的膨胀卷积通道(Skip-convolution)提取电力数据周期信息;再进行特征融合得到Skip-TCN网络,使网络抓取周期规律,增加信息利用长度;最后设计日期编码网络(Time encoding network)捕捉生活周期和季节性特征,与Skip-TCN进行特征融合得到STE-TCN模型,实现对电力负荷数据长序列预测。结果 实验表明:在与TCN模型和传统时序网络的对比下,Skip-TCN的预测精度均有提升,在预测长度更长的测试上提升尤为明显。结论 实验结果验证了通过对更长跨度时序关系的捕捉,STE-TCN网络改进方法有效提升了对长序列电力负荷的预测精度。

药物的定量结构色谱保留关系研究

采用人工神经网络(ANN)建立了110种药物的结构与色谱保留之间的定量关系(QSRR)模型,并将其与偏最小二乘回归(PLSR)模型进行比对.110种药物的ANN模型自相容能力的复相关系数(R^(2))为0.9191,泛化能力的复相关系数(R^(2))为0.9365;而PLSR模型的复相关系数(R^(2))为0.8275和0.8514.结果表明,ANN模型的自相容能力、泛化能力优于PLSR模型.采用集内集和集外集对模型进行检验时,ANN模型的复相关系数(R^(2))为0.9105,也优于PLSR模型,且ANN预测精密度和准确度更高.