基于理性行为理论的微博用户转发行为影响因素研究

发布时间：2018-06-14 06:22

本文选题：理性行为模型 + LDA主题模型　；参考：《情报杂志》2017年11期

【摘要】：[目的/意义]基于理性行为理论分析微博用户转发行为,考虑了微博语义特征、数据形式、用户特征、用户交互等因素,探究了影响用户态度和主观规范的因素对用户转发行为的影响。[方法/过程]在分析微博特征、用户特征及用户转发行为的基础上,基于理性行为理论提出研究假设,采用主题建模的技术研究文本的语义信息,基于LDA进行微博文本与用户兴趣的概率主题分布的训练,基于二元Logistic回归模型对提出的影响因素完成数据验证。[结果/结论]态度因素中,接收用户活跃度、微博文本与用户兴趣的语义相似度对用户转发行为影响显著,微博数据形式对用户转发行为影响不显著;主观规范因素中,发布用户与接收用户交互度对用户转发行为影响显著,发布用户的影响力对用户转发行为影响不显著。研究成果在用户行为预测、微博传播分析等领域可借鉴使用。
[Abstract]:[objective / significance] based on rational behavior theory, Weibo user forwarding behavior is analyzed, and Weibo semantic features, data forms, user characteristics, user interactions and other factors are considered. This paper explores the influence of user attitude and subjective norms on user forwarding behavior. [methods / process] based on the analysis of Weibo features, user characteristics and user forwarding behaviors, the research hypotheses are put forward based on rational behavior theory, and the semantic information of the text is studied by thematic modeling technology. The Weibo text and user interest probability topic distribution are trained based on LDA, and the influence factors are verified based on the binary Logistic regression model. [results / conclusion] among the attitude factors, the activity of the receiving user, the semantic similarity between the Weibo text and the user's interest had a significant effect on the user's forwarding behavior, while the Weibo data form had no significant effect on the user's forwarding behavior. The interaction between the user and the receiver has a significant impact on the user's forwarding behavior, but the impact of the user's influence on the user's forwarding behavior is not significant. The research results can be used in user behavior prediction, Weibo communication analysis and other fields.
【作者单位】：西安电子科技大学经济与管理学院;
【基金】：陕西高校人文社会科学青年英才支持计划(编号:ER42015060001)资助
【分类号】：G206

【相似文献】