基于关系HK模型的群体观点演化建模与仿真

针对传统HK模型中,未考虑个体间人际关系对观点阈值外个体观点交互的影响,提出一种关系HK模型,以研究关系度对群体观点演化时间和系统观点簇的影响,以及关系度在两个意见观点趋向相反的观点领袖及其支持者中发挥的作用。研究结果表明,群体中关系度的存在有利于观点达成共识,缩短系统观点演化时间。特别地,在具有观点领袖的群体中,观点领袖支持者的特征因素对系统观点演化结果起着决定性的作用,如支持者初始观点、观点阈值、关系度阈值和初始观点坚持度。当群体中存在两个意见趋向相反且彼此间没有关系度的观点领袖时,系统最终出现分裂状态,而观点领袖及其支持者之间关系度的存在,有利于系统观点达成共识。     

基于从众行为的改进Hegselmann-Krause观点动力学分析

在许多社交场景中,个体往往因为从众行为而改变自己的观点.为了探究从众行为对个体观点演化的影响,提出具有群体压力的改进Hegselmann-Krause(HK)模型.与已有模型不同,所提出模型中每个个体对其余个体的影响程度并不总是相同.首先,在此基础上,通过理论分析该模型的收敛性,并给出该模型的收敛时间及其与信任边界、群体压力大小等因素的关系;然后,考虑到群体中存在合作和对抗2种关系,进一步提出具有群体压力的改进符号HK模型,验证该模型的收敛性,并给出其收敛时间以及与信任边界、群体压力大小等因素的关系;最后,仿真分析信任边界和群体压力对所提出2种模型的观点演化过程和收敛时间的影响,并验证所提出模型的有效性.结果表明,信任边界与群体压力越大,群体内个体的观点收敛越快.     

基于观点动力学的在线评分人数预测

多数观点动力学研究采用基于Agent的建模和仿真方法,与现实社会现象严重脱节。针对该问题,利用现实社会在线评分的统计数据验证和改进观点动力学模型的解释和预测能力。在评分过程中,个体的观点受到自身初始观点和群体观点的共同影响,产生的最终观点将决定个体是否加入评分群体,如果加入将产生评分行为,进而影响后续个体的观点及行为。据此过程建立一个连续观点动力学模型,对在线评分的人员数量进行预测。使用豆瓣网站的影片在线评分数据进行实验,分析各评分观点变化对在线评分数量的影响,结果表明,该模型能够有效预测在线评分人数;个体的最终观点主要受群体差-中-好评分观点的影响,而与自身初始观点基本无关;泊松参数值偏离最优值越远,预测准确率越低。     

基于观点认同的群体情绪模型

为了能够有效地模拟群体环境中群体情绪的演化过程, 以情绪感染为理论基础, 提出一种新的基于观点认同的群体情绪模型。该模型引入个体观点值、情绪触发阈值来实现观点交互与认同对群体情绪演化所产生的影响作用。观点交互采用有界信任Deffuant模型来实现。通过模拟发现, 观点交互不仅加速了群体情绪融合过程, 而且在多观点群体环境中对群体情绪融合态势也具有决定性的作用。实验模拟结果表明, 本模型不仅能够体现情绪感染过程中个体的无意识、自动感染过程, 而且也能够体现个体对传染对象的选择性过程, 弥补了情绪感染过程中个体无认知的缺陷。     

基于节点亲密度和影响力的社交网络舆论形成模型

针对舆论传播过程中个体交互的广泛性和个体社会影响力的差异性,在Hegselmann-Krause模型的基础上建立了社交网络舆论形成模型。新模型通过引入个体间亲密度、人际相似性和交互强度等概念,对个体交互集合进行了扩展,并对影响力权重进行了合理量化,进而构建更切合实际的观点交互规则。通过一系列仿真实验,分析了模型主要参数在舆论演化中的作用。结果表明：在不同信任阈值下,群体观点均能收敛到一致,形成舆论共识;且信任阈值越大,收敛时间越短;当信任阈值为0.2时,收敛时间仅为10。同时,扩大交互集合、提高人际相似性的作用强度会促进舆论共识的形成。此外,当无标度网络的聚类系数和平均度较高时,群体观点更容易产生趋同效应。研究结果有助于理解舆论形成的动力学过程,对社会管理者进行决策分析具有指导作用。     

邓巴数限制下的社交网络回音室数量研究

大量研究发现，社交网络结构对观点的传播动力学特性有显著影响。提出的基于邓巴数限制的网络生成算法--DNCSN（Social Network Generation Algorithm with the Constraint of Dunbar’s Number），具有较小的平均距离和较大的群聚系数，可以生成与真实网络节点度和节点强度的非线性关系较为接近的结果。基于DNCSN生成算法，可以更为有效地研究社交网络上的观点演化特性。通过调整社交网络中个体的观点“坚定度”和观点取信阈值参数，对比研究了回音室的形成数量变化。研究表明当网络的观点初值均匀分布，网络规模小于邓巴数字时，相比于同等规模的全联通网络，DNCSN网络结构能在节点取信阈值大于0.15时减少网络的回音室的形成数量；当网络规模增大时，DNCSN网络的回音室形成数量多于全联通网络；当取信阈值小于0.1时，全联通网络的回音室形成数量受网络规模影响，且网络规模越小回音室数量越少。     

小世界效应的网络舆情演化迁移元胞模型

依据网民关系网络拓扑的小世界效应特性,提出网民观点的倾向度转换规则,在网络舆情网民关系小世界网络矩阵表示的基础上,构建基于小世界效应的网络舆情演化迁移元胞模型,运用该模型分析网络舆情演化,产生了倾向度转换图、粗细粒度倾向度曲线的仿真结果.通过对试验仿真结果的分析,揭示了网络舆情演化的观点极分化和观点漂移的现象,分析了“核心”区域漂移现象和倾向度曲线多波峰现象的成因,仿真结果表明该模型能较好拟合网络舆情演化的规律.本研究对网络监察部门和新闻管理部门的管理提供了一定的理论依据.     

基于公共邻居的MHK一致性协议及其稳定性分析

如何增强多智能体系统一致性收敛是其一致性研究的重要问题。提出了一种新的MHK（multi-agent-based Hegselmann-Krause）一致性协议,该协议将智能体间的公共邻居作为切换网络下多智能体分布式协作的重要调控因素。针对该协议下的多智能体系统设计了能量函数,分析并证明了该系统具有李雅普诺夫意义下的稳定性,将收敛为一个或多个子观点集群。数值仿真采用增量分析方法考察了系统所收敛的观点集群数量与初始拓扑区间长度的关系;实验表明,该协议使多智能体系统收敛为数量更少的观点集群。所提出的基于公共邻居的MHK一致性协议能够有效提高切换网络的连通性,从而增强系统的一致性收敛,并能为观点演化模型的控制与优化提供理论支撑。     

面向论坛网络的观点传播与舆情形成模型

根据网络论坛的信息传播规律和用户交互特性,提出了一个基于节点影响力的离散时间观点传播与舆情形成模型。在该模型中,节点具有自我影响力和观点值,并且节点影响力被定义为网络中边的权值,节点在每一个周期内重新分配权值并更新它们的观点。节点观点收敛于某一定值时,形成网络舆情。仿真结果表明,所提模型可以准确地体现节点观点的动态交互特性和收敛特征,并可为舆情传播趋势的预测研究提供依据。     

媒体干预及用户信任的网络社区观点演化研究

从信任的角度出发,综合社区内外部因素构建了涉及成员间信任、领袖信任、媒体信任三方面的集成观点演化模型。通过仿真实验模拟社区环境,结果表明：社区内成员互信程度越高,成员观点开放程度越高,则社区观点演化至稳定态的速度越快。社区中意见领袖的作用需要通过长期作用才能突显,维持高程度的领袖信任以及较多的社交联系将有助于领袖引导社区观点向领袖观点靠近。社区成员对媒体的信任程度会影响媒体干预的效果,随着干预程度的增加逆反现象也会更加明显。成员对媒体持正面的印象将有助于社区观点向媒体观点靠近。     

An adaptive group decision making framework: Individual and local world opinion based opinion dynamics

Opinion dynamics (OD) models, which simulate individuals’ opinion evolution process on social network to analyze the final state of opinion distribution in a group, usually differ from each other due to the differences in social network evolution rules and opinion evolution rules. However, most existing social network evolution rules and opinion evolution rules usually cannot characterize the comprehensive influence of key factors such as neighbors and opinion differences in social relationships. To fully consider the properties of social network evolution and improve the efficiency of consensus reaching process in group decision making, this paper introduces the concept of local world opinion derived from individuals’ common friends, and then proposes an individual and local world opinion-based OD model. In the proposed model, social network evolution is jointly determined by the distance between individual opinions and network structure similarity. The pair of individuals with the largest consensus improvement space are then suggested to adjust their opinions by using an adaptive individual opinion adjustment mechanism. Finally, detailed simulation results are provided to demonstrate the convergence of the proposed model and analyze different parameters’ effects on the stabilized time steps and the number of stable state opinion clusters.     

A unified latent variable model for contrastive opinion mining

There are large and growing textual corpora in which people express contrastive opinions about the same topic.This has led to an increasing number of studies about contrastive opinion mining.However,there are several notable issues with the existing studies.They mostly focus on mining contrastive opinions from multiple data collections,which need to be separated into their respective collections beforehand.In addition,existing models are opaque in terms of the relationship between topics that are extracted and the sentences in the corpus which express the topics;this opacity does not help us understand the opinions expressed in the corpus.Finally,contrastive opinion is mostly analysed qualitatively rather than quantitatively.This paper addresses these matters and proposes a novel unified latent variable model(contraLDA),which:mines contrastive opinions from both single and multiple data collections,extracts the sentences that project the contrastive opinion,and measures the strength of opinion contrastiveness towards the extracted topics.Experimental results show the effectiveness of our model in mining contrasted opinions,which outperformed our baselines in extracting coherent and informative sentiment-bearing topics.We further show the accuracy of our model in classifying topics and sentiments of textual data,and we compared our results to five strong baselines.     

粒子群算法优化的BP网络预测软件质量

预测软件质量的技术中,软件建模技术是软件质量评价体系中的关键技术,它可以发现软件中度量数据和软件质量要素之间的非线性关系。BP神经网络能够很好地模拟度量数据和质量要素之间的非线性关系,但是BP网络存在易于陷入局部极小和收敛速度慢的问题,所以提出了用粒子群算法优化BP神经网络,通过优化的BP网络建立软件质量模型,这样能很好地解决BP网络收敛速度慢和局部极小的问题。在实现该进化BP神经网络的基础上,利用28组数据进行实验,并通过与BP模型的结果的比较,验证了该模型。     

Bounded confidence opinion dynamics with opinion leaders and environmental noises

Opinion dynamics is a kind of collective decision-making process and focuses on the study of evolution and formation of opinions within a human society. Particularly, bounded confidence rule is one of intrinsic interaction principles in the opinion dynamics. In this paper, a leader–follower opinion dynamics model is built, with the help of the bounded confidence rule, to consider the opinion formation of a community, which is constituted of opinion leaders and opinion followers. At the same time, environmental uncertainties are considered in the opinion formation and called as environmental noises, which are modeled as Gaussian stochastic processes. All the agents are assumed to have heterogeneous confidence levels. Then the impacts of the opinion leaders and the environmental noises on the final opinions of the opinion followers are analyzed. Finally, some simulation results are presented to demonstrate the collective opinion evolution in three cases: no opinion leader, single opinion leader and multiple opinion leaders.     

Influence identification of opinion leaders in social networks: an agent-based simulation on competing advertisements

In social networks, factors that influence the spread of information are essential for companies to comprehend. This study uses the opinion dynamic theory to investigate the influence of multiple advertisement opinion leaders in social networks. We construct an integrated bounded confidence model to simulate the evolution of followers’ opinions under two advertisement opinion leaders. Through experimental simulation, we found that the weight of influence on advertisements has a dual effect on the evolution of followers’ opinions, and the probability that information is transmitted by opinion leaders has a significant impact on the evolution of collective opinions. The results show that, for competitive products, companies should properly understand the propaganda power of product advertisements and improve the probability of information being successfully transmitted by opinion leaders.