Exploring Scientific Literature Search through Topic Models
Exploring Scientific Literature Search through Topic Models
复制标题
通过主题模型探索科学文献检索
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
D. Glowacka
中科院分区：
文献类型：
--
作者：
Amin Sorkhei;K. Ilves;D. Glowacka
随着科学文献数量的快速增长，浏览这些文献可能是一项艰巨的任务：由于新的研究领域迅速涌现，而且经常使用不同的术语来描述同一概念，制定准确的查询可能会遇到问题。为了解决其中的一些问题，我们建立了一个基于主题模型的探索性科学搜索系统。一项初步的短期用户研究表明，与仅基于搜索查询的传统系统相比，通过可视化关键短语、文档和作者之间的关系，该系统允许用户更好地探索文档搜索空间。
With the fast growing amount of scientific literature, browsing through it can be a dicult task: formulating a precise query may be problematic as new research areas emerge quickly and different terms are often used to describe the same concept. To tackle some of these issues, we built a system for exploratory scientific search based on topic models. An initial short user study shows that through visualizing the relationship between keyphrases, documents and authors, the system allows the user to better explore the document search space compared to traditional systems based solely on search query.