A Multi-Agent School Simulation Based on Hierarchical Social Networks

The quality of K-12 education has been a very big concern for years. Previous methods studied only one or two factors, such as school choice, or teacher quality, on school performance. Therefore the results they provide can be limited. We propose a multi-agent approach to integrate multiple actors in a school system. These actors include teachers, students, supporting staffs and administrators. The interactions among these actors compose a hierarchical school social network. We first detect the hierarchical community structure in this school network by using an agglomerative hierarchical algorithm. Existing agglomerative hierarchical algorithms usually calculate similarity or dissimilarity between two clusters by using some measure of distance between pairs of observations. We, however, develop a method that calculates similarity based on social interactions between interactions is essential in multi-agent systems. Our algorithm is applied to 15 school districts in Bexar County, Texas, and it provides satisfying results on generating the hierarchical structure of all school districts. We then use the detected structure of the social network to evaluate the school system’s organization performance. We design and implement a funding evaluation model to decompose the funding policy task into subtasks and then evaluate these subtasks by using funding distribution policies from past years and looking for possible relationships between student performances and funding policies. Experiments in the 15 school districts in Bexar County show no significant correlation between student performance and the amount of the funding a school district received.

基于Social Transformer的井下多人轨迹预测方法

目前煤矿井下人员轨迹预测方法中,Transformer与循环神经网络(RNN)、长短期记忆(LSTM)网络相比,在处理数据时不仅计算量小,同时还有效解决了梯度消失导致的长时依赖问题。但当环境中涉及多人同时运动时,Transformer对于场景中所有人员未来轨迹的预测会出现较大偏差。并且目前在井下多人轨迹预测领域尚未出现一种同时采用Transformer并考虑个体之间相互影响的模型。针对上述问题,提出一种基于Social Transformer的井下多人轨迹预测方法。首先对井下每一个人员独立建模,获取人员历史轨迹信息,通过Transformer编码器进行特征提取,接着由全连接层对特征进行表示,然后通过基于图卷积的交互层相互连接,该交互层允许空间上接近的网络彼此共享信息,计算预测对象在受到周围邻居影响时对周围邻居分配的注意力,从而提取其邻居的运动模式,继而更新特征矩阵,最后新的特征矩阵由Transformer解码器进行解码,输出对于未来时刻的人员位置信息预测。实验结果表明,Social Transformer的平均位移误差相较于Transformer降低了45.8%,且与其他主流轨迹预测方法LSTM,S−GAN,Trajectron++和Social−STGCNN相比分别降低了67.1%,35.9%,30.1%和10.9%,有效克服了煤矿井下多人场景中由于人员间互相影响导致预测轨迹失准的问题,提升了预测精度。

基于Multi-agent理论的社会网络文体分类方法

针对当前社会网络中的文体分类存在分类效果不理想问题,结合网络文体的多样性、多归属性及动态性的特征,提出了一种基于multi-agent的属性融合和词库关联的网络文体分类方法.首先提取网络文体的特征关键词和词义等基本属性,建立Multi-agent的融合分类模型,并给出了基于Multi-agent的社会网络文体融合分类算法.实验结果表明该方法与传统单分类器以及其他多分类器融合分类方法相比,不仅可以通过语义特征提取对语义网络中的网络文体进行高精度分类,而且可以实现社会网络文体分类的自动化,具有更高的分类精度与稳定性.

Social organization of Shortridge’s capped langur（Trachypithecus shortridgei） at the Dulongjiang Valley in Yunnan,China

Non-human primates often live in socially stable groups characterized by bonded relationships among individuals. Social organization can be used to evaluate living conditions and expansion potential. Bisexual group size, ratio of males to females and group composition are essential elements determining the type of social organization. Although the first report on Shortridge’s capped langurs（Trachypithecus shortridgei） was in the 1970 s, until now, the species only inhabits forests of the Dulongjiang valley in northwest Yunnan, China, with c. 250-370 individuals in 19 populations. To understand its social organization, we collected data from five groups of Shortridge’s langurs at Silaluo in the Dulongjiang valley during August 2012-October 2013. Family groups consist of one adult male, 2–3 adult females and up to five young. Group size averaged 8（7-9） individuals. The ratio of adult males to females（M/F） was 1：2.9, infants to adult females was（I/F） 1：2.2; and ratio of adults to immatures was 1：1.2, indicating the potential of a population increasing. Birth season was during March-July and the inter-birth interval was two years.

Dynamic programming methodology for multi-criteria group decision-making under ordinal preferences

A method of minimizing rankings inconsistency is proposed for a decision-making problem with rankings of alternatives given by multiple decision makers according to multiple criteria. For each criteria, at first, the total inconsistency between the rankings of all alternatives for the group and the ones for every decision maker is defined after the decision maker weights in respect to the criteria are considered. Similarly, the total inconsistency between their final rankings for the group and the ones under every criteria is determined after the criteria weights are taken into account. Then two nonlinear integer programming models minimizing respectively the two total inconsistencies above are developed and then transformed to two dynamic programming models to obtain separately the rankings of all alternatives for the group with respect to each criteria and their final rankings. A supplier selection case illustrated the proposed method, and some discussions on the results verified its effectiveness. This work develops a new measurement of ordinal preferences’ inconsistency in multi-criteria group decision-making （MCGDM） and extends the cook-seiford social selection function to MCGDM considering weights of criteria and decision makers and can obtain unique ranking result.

The Construal of Multi-modal Metaphor in Public Service Advertisements between China and America

Based on the theory of Forceville’s multi-modal metaphor,this paper adopts qualitative and quantitative research methods to analyze 60 social safety ads both in China and America,trying to demonstrate the similarities and differences between the chosen social safety ads in using multi-modal metaphor and discussing the factors that caused these differences.

Mechanisms for Cross-Scaling, Flexibility and Social Learning in Building Resilience to Sea Level Rise: Case Study of Hampton Roads, Virginia

This case study examines how the Hampton Roads Sea Level Rise Preparedness and Resilience Intergovernmental Planning Pilot Project, a whole-of-government and whole-of-community approach to planning for and adapting to sea level rise, addressed coastal resilience in a southeastern Virginia watershed that spans multiple jurisdictions. Meeting the challenge of sea level rise requires that actors across multiple sectors—citizens, community organizations, industry and government—understand the risks and work together to make critical decisions regarding adaptation strategies and actions. The case study area includes Little Creek Amphibious Base, which is bordered by the cities of Norfolk and Virginia Beach. Adaptation responses to sea level rise by the military base and the local governments will impact each other and the residents of the area, but no cooperative agreements are in place for a joint or collaborative response. This case study examines public and private infrastructure at risk, the infrastructure interdependencies, and mechanisms for providing collaborative solutions. Engagement of area residents and other stakeholders is also integral to the process of adaptation, which includes educating about sea level rise risk and provides a mechanism for social learning that enables stakeholders to participate in critical adaptation decisions. The case study demonstrates a method to improve resiliency in the case study area and inform a regional, multi-sectoral response to sea level rise adaptation strategies.

Research community detection from multi-relation researcher network based on structure/attribute similarities

Purpose: This paper aims to provide a method to detect research communities based on research interest in researcher network, which combines the topological structure and vertex attributes in a unified manner.Design/methodology/approach: A heterogeneous researcher network has been constructed by combining multiple relations of academic researchers. Vertex attributes and their similarities were considered and calculated. An approach has been proposed and tested to detect research community in research organizations based on this multi-relation researcher network.Findings: Detection of topologically well-connected, semantically coherent and meaningful research community was achieved.Research limitations: The sample size of evaluation experiments was relatively small. In the present study, a limited number of 72 researchers were analyzed for constructing researcher network and detecting research community. Therefore, a large sample size is required to give more information and reliable results.Practical implications: The proposed multi-relation researcher network and approaches for discovering research communities of similar research interests will contribute to collective innovation behavior such as brainstorming and to promote interdisciplinary cooperation.Originality/value: Recent researches on community detection devote most efforts to singlerelation researcher networks and put the main focus on the topological structure of networks.In reality, there exist multi-relation social networks. Vertex attribute also plays an important role in community detection. The present study combined multiple single-relational researcher networks into a multi-relational network and proposed a structure-attribute clustering method for detecting research community in research organizations.

Modeling for heterogeneous multi-stage information propagation networks and maximizing information

In this paper, we propose a heterogeneous multi-stage model to study the effect of social reinforcement on information propagation. Both heterogeneity of network components and the heterogeneity of individual reinforcement thresholds are considered. An information outbreak condition is derived, according to which the outbreak scale and individual density of each state under specific propagation parameters can be deduced. Monte Carlo experiments are conducted in Facebook networks to demonstrate the outbreak condition, and we find that social reinforcement effects generally inhibit the propagation of information though it contributes to the emergence of certain hot spots simultaneously. Additionally, by applying Pontryagin's Maximum Principle, we derive the optimal control strategy in the case of limited control resources to maximize the information propagation. Then the forward–backward sweep method is utilized to verify its performance with numerical simulation.

Energy-Aware Multi.Replica Routing in Delay Tolerant Mobile Sensor Network

The two-phase replication-based routing has great prospects for Delay Tolerant Mobile Sensor Network (DTMSN) with its advantage of high message delivery ratio, but the blind spraying and the low efficiency forwarding algorithm directly influences the overall network performance. Considering the characteristic of the constrained energy and storage resources of sensors, we propose a novel two-phase multi-replica routing for DTMSN, called Energy-Aware Sociality-Based Spray and Search Routing (ESR), which implements the quota-style message replication mechanism by utilizing the energy and speed information of sensors. In addition, based on the difference of history encounters, a sociality metric is defined to improve the forwarding efficiency in search phase. Simulation experiments show that ESR can reduce the message delay and improve the resource utilization while maximizing the message delivery ratio compared with the exiting popular two-phase routing protocols.

Deterministic Multicultural Dynamic Networks: Seeking a Balance between Attractive and Repulsive Forces

An important issue in society is the attempt to balance communities working co-operatively and cohesively with one another while allowing members the ability to retain individuality and fostering an environment of cultural diversity. We seek to study the cohesive properties of a culturally diverse dynamic social network. By considering a multi-agent dynamic network, we seek to model a social structure and find conditions under which cohesion and coexistence are maintained. We present a specific illustration that serves to establish the framework in which explicit sufficient conditions in terms of system parameters are found for which the network is cohesive. By utilizing Lyapunov’s Second Method and comparison equations, we are able to find such conditions for the given illustration. Further, for the illustration, we decompose the cultural state domain into invariant sets and consider the behavior of members within each set. Moreover, we analyze the relative cultural affinity between individual members relative to the center of the social network. We also demonstrate how conservative the estimates are using Euler type numerical approximation schemes based on the given illustration. We are then able to consider how changes in the various parameters affect the dynamics of the illustrated network. By gaining such insight into the behavior of the illustrated network, we are able to better understand the impact of both attractive and repulsive influences on the network. This leads to establishing a schema for helping when creating policies and practices catered to promoting both diversity and cohesion within a cultural network.

劳动者创业与多层次社会保险需求——基于中国家庭金融调查数据的实证研究

采用2013—2017年中国家庭金融调查(CHFS)数据,实证检验自主创业对多层次社会保险需求的影响。研究发现:个体进行自主创业后的多层次社会保险需求会显著提高,增加幅度平均为3.29个百分点。相比于受雇个体,年龄在45~59岁且收入处于中等水平的发展型创业个体具有更高的多层次社会保险需求。在保险类型上,自主创业个体对多层次养老保险的需求最高,而对多层次医疗保险的需求较低。自主创业个体还会提高其家人的多层次社会保险需求,配置顺序依次是青壮年、老年人和儿童。

地理知识图谱增强与多时空条件约束的轨迹预测

基于机器学习的轨迹预测方法通常依赖历史轨迹数据的数量和质量,而社交媒体签到数据更新频率低,形成的轨迹稀疏,在预测中易出现难学习、过拟合等问题。为突破低质量轨迹数据在预测任务中的限制,本文提出一种基于地理知识图谱增强与多时空约束条件建模的轨迹预测方法。将复杂异构的多源地理信息结构化为由若干三元组构成的地理知识图谱进行统一表达,并通过知识表示模型挖掘其中语义关联来增强轨迹序列的向量表征,同时采用具有多重时空约束条件的多头自注意力机制提取稀疏轨迹序列中的多重时空特征,从而提升轨迹预测精度。研究采用纽约市Foursquare社交媒体签到数据进行方法验证,试验结果表明:本文方法相较于其他表示学习方法和轨迹预测方法,在命中率和平均倒数排名两个评价指标上均有不同程度的提升,能够有效增强稀疏轨迹序列的表征,提取轨迹的多重时空特征,提高社交媒体用户签到轨迹的预测精度。

新时代我国竞技体育发展中政社关系改革的几点思考

为更好适应新时代社会主要矛盾变化,建构我国竞技体育发展新格局,采用文献资料法和访谈法对我国竞技体育发展中政社关系改革问题进行分析。认为,我国竞技体育发展中强政府、弱社会的发展惯性仍需进一步打破,社会自组织的发展能力有待提高,政府管理的角色和职能亟需转变。新时代我国竞技体育发展需重视政社关系改革,从强政府、弱社会转变为强政府、大社会发展格局,政府引导社会力量有序发展,并与社会力量合作构建多元治理机制。具体包括:深化“放管服”改革,竞技体育“举国体制”继续做减法;社会力量加强自身建设,在更多领域发挥更大作用;依据经济发展的阶段性特征,有针对性地扶持社会力量成长;根据参与类别,对社会力量发展提供差异化的帮扶;做好市场监管,引导、规范社会力量成长;积极推进政府元治理、行业自治和多元共治。

基于多模态掩码Transformer网络的社会事件分类

多模态社会事件分类的关键是充分且准确地利用图像和文字2种模态的特征。然而,现有的大多数方法存在以下局限性:简单地将事件的图像特征和文本特征连接起来,不同模态之间存在不相关的上下文信息导致相互干扰。因此,仅仅考虑多模态数据模态间的关系是不够的,还要考虑模态之间不相关的上下文信息(即区域或单词)。为克服这些局限性,提出一种新颖的基于多模态掩码Transformer网络(MMTN)模型的社会事件分类方法。通过图-文编码网络来学习文本和图像的更好的表示。将获得的图像和文本表示输入多模态掩码Transformer网络来融合多模态信息,并通过计算多模态信息之间的相似性,对多模态信息的模态间的关系进行建模,掩盖模态之间的不相关上下文。在2个基准数据集上的大量实验表明:所提模型达到了最先进的性能。

中国式现代化导向的市域社会治理及多主体协同的路径优化研究

市域社会治理包含于中国式现代化的体系框架之下,后者之于前者具有战略和实践层面的引领意义。从理论逻辑看,市域社会治理在国家治理体系与治理能力现代化实践中,具有承上启下的战略地位,对实现全过程人民民主、建立合作共赢的开放治理格局具有推动作用。从实践逻辑看,实现市域社会治理离不开多元主体协同,要求在推进治理要素、治理方式、治理机制等方面取得更加务实的成果。在理顺两者关系的基础上,本研究梳理出市域社会治理的客观诉求,认为实现具有中国式现代化特色的市域社会治理需要以多主体协同为切入点,并针对性提出了市域社会治理多主体协同的路径优化举措。

大学生社会适应发展趋势的多层线性模型研究

目的:以多层线性模型的方法探究大学生社会适应的发展趋势及其个体间的差异。方法:采用中国大学生适应量表(CCSAS)对2994名大学生进行了社会适应的现状及发展研究,并从各个学院共选取了665名学生作为对象,进行为期1年的追踪调查,最后用HLM软件进行数据分析。结果:①大学生社会适应的总体是中等偏上的,并存在性别上的显著差异(t=-4.863,P<0.001);②社会适应水平随时间发展有显著的上升趋势,平均上升速度为0.185(SE=0.052,P<0.01);③性别(t=-2.631,P<0.01)和民族(t=-2.516,P<0.05)对大学生的社会适应具有显著的预测作用。结论:大学生社会适应水平会随时间发展呈现上升趋势。

国内智慧教育领域研究热点与趋势

近年来,智慧教育的兴起引起人们的广泛关注。本文以2013—2022年CSSCI数据库中关于智慧教育的572篇文献的高频关键词为原始数据,运用Bibexcel、Ucinet和SPSS软件对高频关键词数据进行共词分析、社会网络分析、多维尺度分析和聚类分析,揭示智慧教育领域的研究热点和发展趋势。研究结果显示智慧教育研究的热点主要体现在:教育信息化、教育现代化等政策、战略;智慧教育的内涵、特征、功能等;智慧教育的体系架构与智慧环境建设等;智慧教育的技术支撑及实践。本文还基于智慧教育研究现状,提出未来发展需要关注的四个方向。

基于深度学习节点表示的谣言源定位方法

随着互联网的普及,网络上的信息以惊人的速度传播给公众。然而,由于级联效应,虚假信息和谣言同时也在迅速蔓延,对社会造成了巨大的危害。在社交网络上找到谣言的传播源头,对抑制谣言的传播起到至关重要的作用。传统的谣言源定位方法大多未能够融合多源特征且定位准确率还需进一步提高,因此,提出一种基于深度学习的谣言源定位方法,根据观测受谣言影响的节点多源特征来识别谣言源。首先,根据节点与观测节点之间的影响力相似度得到节点的影响力向量。然后,利用自编码网络对节点的影响力向量进行编码,得到包含节点信息、扩散路径和传播时间信息在内的节点的新的嵌入表示。最后,根据节点新的影响力向量计算节点为谣言源的概率,以定位谣言源。在2个模拟网络和4个真实网络上的实验结果表明,与其他方法相比,所提方法能够以更快的速度定位谣言源,且谣言源定位的准确率提升了25%以上。

农村社会养老保险对农户多维相对贫困的影响研究

农村社会养老保险对于提升家庭内生发展能力,缓解农户多维相对贫困具有重要意义。基于可行能力理论构建多维相对贫困指数,利用2014—2018年三期中国家庭追踪调查数据库,探究农村社会养老保险对农户多维相对贫困的政策效果及作用机制。结果表明,农村社会养老保险能够通过促进老年人操持家务、隔代照顾和促进青年劳动力外出就业缓解家庭多维相对贫困状况。按照农村社会养老保险的边际效果特征,农户群体可被划分为有效型、抑制型与无效型三种,且在样本期间内抑制型农户减少,无效型农户增多。另外,农村社会养老保险仅对于多维相对贫困程度较高的农户有显著的作用效果,且农村社会养老保险能够阻断返贫以及抑制长期性贫困。因此,为有效缓解农户多维贫困,应推动农村产业发展并加强对农村劳动力的技能培训,完善农村社会养老保险制度的运作模式和提升养老金待遇水平,以及构建多元化农村社会保障制度。