2011年12月11日

如何在“数字人文科学”中进行智能文本分析?

在一个人可以回答这个问题之前’s necessary to provide a conceptual picture of what the Humanities actually mean and encompass. 的New Oxford American Dictionary defines Humanities as the arts: liberal arts, literature, history, philosophy, classical studies, and classical literature. So Humanism as a field of study is complex and multidisciplinary by definition, a multi-faceted, all-encompassing and overlapping field.

的‘digital’ in humanities denotes the metamorphosis (or recasting for want of a better word) of text through the process of methodical digitisation. 的idea is to increase, qualitatively as well as quantitatively, access to cultural information via computational means. It also means transformation of scholarly communication by embracing multi-media, hyperlinking, social media (blogging, YouTube, Flickr, delicious, Twitter, collaborative annotation…)和有效的网络搜索。从某种意义上说,这也影响了研究,教学活动,基于社区的学习和合作的范围和机会也在不断发展。

All of this is realised through the cooperative effort of humanists, IT technicians, librarians, archivists, students, and members of the public. Why the public? 的public contributes valuable cultural materials that would otherwise remain undetected and inaccessible to interested audiences. A random example of constructive public participation would be Europeana’s recently launched 图片,信件和回忆档案中的第一次世界大战 (另请参阅以前的博客条目 )。

From a pragmatic perspective, 研究 within the 数字 humanities environment requires effective management of electronic texts. 塔波 是一个在线门户和正在进行的协作项目,它提供了用于复杂文本分析和检索的工具。它为用户提供了一个在线环境,用于跟踪他们想学习的文本(位于网络上或上传的文本)并以不同的方式进行分析。本质上,计算机辅助的文本分析环境已经超越了‘Find’通用文字处理器的工具。它们为研究人员提供了一种以多方面的方式分析大型文本的方法,并允许搜索单词列表和复杂的单词模式。至关重要的是,文本分析结果可以通过多种方式显示。

因此,例如可以雇用 塔波 门户网站食谱  to locate and identify themes within a text or aggregate information to explore a concept. It is also possible to filter for specific themes or analyse theoretical foundations in a given text. 的portal is expansive and offers a variety of analytical templates.

继续取样...

参考

0 comments:

发表评论