摘要
【目的/意义】掌握微博热点话题演化规律有利于让公众了解正确的话题演化方向,也便于有关部门对舆情监控和引导,使得舆论朝着正能量的方向发展。【过程/方法】利用OLDA(On-line Latent Dirichlet Allocation)可以实时地追踪热点话题演化的优势以及微博的"话题标签"的特性提出适合微博的热点话题演化模型LOLDA(Label On-line Latent Dirichlet Allocation),然后通过Python编程爬取了新浪微博的数据,从话题内容和强度两方面分析了话题演化规律,并对话题内容演化规律进行了可视化展示。【结果/结论】改进的LOLDA模型可以准确地发现微博话题演化规律,通过实验验证了本文提出的模型较传统模型具有更好地泛化能力。
【Purpose/significance】Grasping the evolution of hot topics in micro-blog will help the public understand the correct direction of topic evolution and facilitate the monitoring and guidance of relevant departments on public opinion so that public opinion will move in the right direction.【Method/process】Proposing a hot topic evolution model of micro-blog-Label On-line Latent Dirichlet Allocation(LOLDA).By combining OLDA(On-line Latent Dirichlet Allocation) can automatically track the evolution of hot topics and the characteristics of micro-blog ’s unique topic label,we propose a hot topic evolution model which is suitable for micro-blog.Then the data of Sina Weibo is crawled through Python programming.The evolution of topics is analyzed in terms of topical content and intensity,and the evolution of topics is visualized.【Result/conclusion】The improved LOLDA model can accurately discover the evolution rules of microblog topics.It is verified through experiments that the proposed model has better generalization ability than the traditional model.
作者
李慧
王丽婷
LI Hui;WANG Li-ting(School of Economics and Management,Xidian University,Xi'an 710071,China)
出处
《情报科学》
CSSCI
北大核心
2019年第1期30-36,共7页
Information Science
基金
国家自然科学基金青年基金项目“大规模动态社交网络社团检测算法研究”(71401130)
关键词
话题演化
话题标签
主题模型
微博话题
topic evolution
topic label
topic model
micro-blog topic