arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1409.7591cs.CLcs.HCcs.IRcs.SIstat.ML
收藏

主题相似性网络:大型文档集的可视化分析

Topic Similarity Networks: Visual Analytics for Large Document Sets

Institute for Defense Analyses(国防分析研究所)

Arun S. Maiya, Robert M. Rolfe

摘要:

我们研究的方法,以提高LDA主题模型的可解释性,更好地分析和可视化其输出。我们专注于研究我们所说的主题相似性网络:图中的节点代表文本集合中的潜在主题,链接代表主题之间的相似性。我们描述了高效和有效的方法来构建和标记这样的网络。基于这些网络的主题模型的可视化被证明是探索,表征和总结大量非结构化文本文档的强大手段。它们有助于“梳理”不同文档集之间的非明显联系,并提供有关主题如何形成更大主题的见解。我们通过两个案例研究证明了这些方法的有效性和实用性:1)NSF资助的基础研究跨越14年的时间和2)维基百科的整个英文部分。

英文摘要:

We investigate ways in which to improve the interpretability of LDA topic models by better analyzing and visualizing their outputs. We focus on examining what we refer to as topic similarity networks: graphs in which nodes represent latent topics in text collections and links represent similarity among topics. We describe efficient and effective approaches to both building and labeling such networks. Visualizations of topic models based on these networks are shown to be a powerful means of exploring, characterizing, and summarizing large collections of unstructured text documents. They help to "tease out" non-obvious connections among different sets of documents and provide insights into how topics form larger themes. We demonstrate the efficacy and practicality of these approaches through two case studies: 1) NSF grants for basic research spanning a 14 year period and 2) the entire English portion of Wikipedia.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑