Exploratory Thematic Analysis for Digitized Archival Collections
Exploratory Thematic Analysis for Digitized Archival Collections
复制标题
数字化档案馆藏的探索性主题分析
DOI：
10.1093/llc/fqv052
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Iris Sun
中科院分区：
文献类型：
--
作者：
Lauren F. Klein;Jacob Eisenstein;Iris Sun
人文学者如何理解新的或不熟悉的档案？计算文本分析在语义生成过程中是否有作用？我们认为，当主题建模被视为主题探索的过程时，可以为这一过程提供一个新的切入点。为此，我们提出了一个名为TOME的新软件工具的研究：交互式主题模型和元数据可视化，旨在支持数字化档案馆藏的探索性主题分析。TOME以一组可视化为中心，旨在促进主题模型的解释，并将其纳入现有的人文研究实践。与其他以自己的方式呈现模型的主题模型创建者不同，我们的主题模型是通过进行早期人文研究的过程来提供信息的。因此，我们的文章也展示了跨学科协作所必需的概念转换——从设计和过程两个方面来看。在明确这些转换，并探索其成功和失败的含义，我们接受了约翰娜·德鲁克（人文学科方法图形显示）的呼吁。数字人文季刊，5(1),2011)，抵制可视化的“知识特洛伊木马”。我们试图建立一种跨学科研究的新模式，这种模式将数字人文学科的方法论重点带到人文学科研究和计算机科学的实践中。
How do humanities scholars make sense of new or otherwise unfamiliar archives? Is there a role for computational text analysis in the process of sensemaking? We propose that topic modeling, when conceived as a process of thematic explor- ation, can provide a new entry point into this process. To this end, we present research on a new software tool called TOME: Interactive TOpic Model and MEtadata Visualization, designed to support the exploratory thematic analysis of digitized archival collections. TOME is centered around a set of visualizations intended to facilitate the interpretation of the topic model and its incorporation into extant humanities research practices. In contrast to other topic model brow- sers, which present the model on its own terms, ours is informed by the process of conducting early-stage humanities research. Our article thus also demonstrates the conceptual conversions—in terms of both design and process—that interdis- ciplinary collaboration necessarily entails. In making these conversions explicit, and exploring the implications of their successes and failures, we take up the call, as voiced by Johanna Drucker (Humanities approaches to graphical display. Digital Humanities Quarterly, 5(1), 2011), to resist the 'intellectual Trojan horse' of visualization. We seek to model a new mode of interdisciplinary inquiry, one that brings the methodological emphasis of the digital humanities to bear on the practices of humanities research and computer science alike.