Identifying Historical Travelogues in Large Text Corpora Using Machine Learning
Identifying Historical Travelogues in Large Text Corpora Using Machine Learning
复制标题
DOI：
10.1007/978-3-030-43687-2_67
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
Jan Rörden;Doris Gruber;Martin Krickl;Bernhard Haslhofer
中科院分区：
文献类型：
--
作者：
Jan Rörden;Doris Gruber;Martin Krickl;Bernhard Haslhofer
游记代表了人文学者的一个重要和深入研究的来源，因为它们提供了对过去的人，文化和地方的见解。然而，现有的研究很少使用十几个主要来源，因为人类处理大量历史来源的能力自然是有限的。在本文中，我们定义的概念oftravelogue和报告后，跨学科的方法，使用机器学习以及领域知识，可以有效地识别德国游记在奥地利国家图书馆的数字化库存与F1分数在0.94和1.00之间。我们将我们的方法应用于161，522个德语卷的语料库，并确定了345个无法使用传统搜索方法识别的游记，从而产生了有史以来最广泛的早期现代德国游记集。据我们所知，这是第一次这样的方法被实施为这样的规模的文本语料库的书目索引，改进和扩展的人文学科的传统方法。总的来说，我们认为我们的技术是一个重要的第一步，在更广泛的努力，开发一种新的混合方法的方法进行大规模的系列分析的游记。
Travelogues represent an important and intensively studied source for scholars in the humanities, as they provide insights into people, cultures, and places of the past. However, existing studies rarely utilize more than a dozen primary sources, since the human capacities of working with a large number of historical sources are naturally limited. In this paper, we define the notion oftravelogueand report upon an interdisciplinary method that, using machine learning as well as domain knowledge, can effectively identify German travelogues in the digitized inventory of the Austrian National Library with F1 scores between 0.94 and 1.00. We applied our method on a corpus of 161,522 German volumes and identified 345 travelogues that could not be identified using traditional search methods, resulting in the most extensive collection of early modern German travelogues ever created. To our knowledge, this is the first time such a method was implemented for the bibliographic indexing of a text corpus on this scale, improving and extending the traditional methods in the humanities. Overall, we consider our technique to be an important first step in a broader effort of developing a novel mixed-method approach for the large-scale serial analysis of travelogues.