人际关系网络中个体关系建模研究

发布时间：2018-06-05 11:29

本文选题：社会网络 + 建模　；参考：《华中科技大学》2012年硕士论文

【摘要】：人际传播是最基本的信息传播方式，渗透于人们的生活之中。人际传播嵌入在人际关系中，同时也会影响个人的人际关系。对人际关系的研究对研究人际信息传播的机制有重要的意义。人际传播蕴含情感的因素，个体间的人际关系对于传播过程中传播者的传播意向与接受者的信任程度均有重要影响。信息传播者通常会倾向于将信息向与自己关系密切的人传播，由于不同的关系类型承载着不同的资源和功用，在信息的传播过程中，个体也会根据关系的内容，选择不同的群体进行传播。基于以上的分析，本文提出了对个体间关系类型与关系强度进行划分的思路。本文采用社会网络分析的方法，根据不同关系类型群体的形成原因和特征提出了判断关系类型的解释变量，根据文献总结提出了关系强度的解释变量。采用问卷调查方法，，使用个人中心网络的提名生成法和提名诠释法收集数据。对变量进行描述统计、相关性检验、共线性检验和logistic回归分析，建立关系类型与关系强度的回归模型，模型的正判率均比较理想。将上述得到的划分模型应用于人际关系网络建模中。首先生成个体模型，以第五次人口普查数据作为依据，制定个体模型的生成规则。开发了能够根据实验情景灵活生成个体模型的平台。所生成的个体模型的特征变量设置合理。然后在仿真平台中将logistic回归模型应用到演化完成的人际关系网络中，判断出每两个相连个体之间的关系类型与关系强度，关系信息使用标签标注显示。最后对网络中个体间的关系进行分析，结果显示不同关系类型间的关系强度分布与调查数据相符，个体间的关系强度符合局部桥的弱关系假设以及禁现三方关系假设，证实了模型的合理性。
[Abstract]:Interpersonal communication is the most basic way of information dissemination, permeating people's life. Interpersonal communication is embedded in interpersonal relationships and also affects personal relationships. The study of interpersonal relationship is of great significance to the study of the mechanism of interpersonal information dissemination. Interpersonal communication contains emotional factors, and interpersonal relationships between individuals have an important impact on the communication intention of the communicator and the degree of trust of the recipient. Information communicators usually tend to spread information to people who are close to themselves. Because different types of relationships carry different resources and functions, individuals will also according to the content of the relationship in the process of information dissemination. Select different groups to spread. Based on the above analysis, this paper puts forward the idea of dividing the types and intensity of relationships between individuals. In this paper, the method of social network analysis is used to put forward the explanatory variables to judge the relationship types according to the formation reasons and characteristics of the groups of different relation types, and the explanatory variables of the relationship intensity are put forward according to the summary of the literature. The method of questionnaire survey was used to collect data using nomination generation method and nomination interpretation method of personal center network. The regression model of relationship type and relationship strength is established by descriptive statistics, correlation test, collinear test and logistic regression analysis. The positive judgment rate of the model is all satisfactory. The proposed partitioning model is applied to interpersonal network modeling. Firstly, the individual model is generated, and the rules of individual model generation are established on the basis of the fifth census data. A platform is developed to flexibly generate individual models according to experimental scenarios. The characteristic variables of the generated individual model are set reasonably. Then the logistic regression model is applied to the evolving interpersonal network in the simulation platform to judge the relationship type and the relationship strength between each two connected individuals. The relationship information is displayed with label. Finally, the relationship between individuals in the network is analyzed. The results show that the relationship intensity distribution between different relationship types is consistent with the survey data, and the relationship strength between individuals accords with the weak relationship hypothesis of local bridge and the prohibitive tripartite relationship hypothesis. The rationality of the model is verified.
【学位授予单位】：华中科技大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：C912.1;G206

【参考文献】