SBE-UKRI: Understanding imprecise space and time in narratives through qualitative representations, reasoning, and visualisation

人类的经历大多以文本的形式被记录和交流，这些文本越来越多地被用作数字语料库。社会科学、人文科学和计算机科学的研究人员面临的一个主要挑战是如何在跨学科的环境中使用这些文本来发展对所描述的经验的有凝聚力的理解。近年来，在地理信息科学（GISc）、语料库语言学、自然语言处理（NLP）、人文地理学、文学研究和数字人文科学等不同领域，对文本来源中的地理理解受到了大量的研究兴趣。目前的技术水平包括使用地质解析来自动识别文本中的地名并将其分配到坐标（Grover et al . 2010）。一旦以这种方式进行地理参考，就可以将地名读入地理信息系统，用于绘图和空间分析。还可以使用语料库语言学和自然语言处理技术进行分析，以查看与地名相关的单词或主题，例如与美丽或激发恐惧等情绪反应相关的地方。这种方法的组合被称为地理文本分析（GTA） （Gregory et al . 2015）。虽然GTA为理解语料库中的地理位置提供了一个有用的起点，但它是高度定量的，仅限于可以找到坐标的命名地点，并且几乎没有时间概念。然而，正如旅行的叙述充分表明的那样，人类对地理的体验往往是主观的，更适合于定性的表现。在这些情况下，“地理”并不局限于命名的地方；相反，它包含了模糊、不精确和模棱两可的内容，例如“营地”、“远处的山丘”或“路的尽头”，并使用诸如“靠近”、“在左边”或“几个小时的车程”等术语包括相对位置。这些定性表示是必要的上下文参考，但不能在地理信息系统等地理空间技术中进行管理。为了大规模地理解人类描述和联系周围世界的方式，我们需要能够直观地表达和解释作者所描述的地理，将所描述的空间体验的定性本质与可定量分析的方法相结合。在一个强大的跨学科团队中，这项资助将开发方法，使我们能够识别、提取、可视化和分析地点和时间的定性和定量参考。这些方法将用于分析两个大型语料库：一个是关于英国湖区的旅行写作语料库，主要写于18和19世纪；另一个是大屠杀幸存者证词的文集。尽管基于非常不同的旅行类型——休闲旅行和被迫迁移——这两个语料库都代表了一系列独特的声音，这些声音融合在一起，产生了复杂的文化和体验地理。该项目将探索来自NLP、语料库语言学、定性时空推理（QSTR）、GISc和视觉分析的尖端数字技术如何帮助我们理解作者自己如何表现他们周围的地理环境，并探索这些文本中所包含的地方感觉和经验的个体和总体表现。由此产生的应用将对学术和非学术受众都具有重要意义。

Human experiences are recorded and communicated mostly as text which are increasingly available as digital corpora. A major challenge for researchers in the social sciences, humanities and computer sciences is how to use these texts in interdisciplinary settings to develop cohesive understandings of the experiences described. Understanding geographies in textual sources has received a significant amount of research interest in recent years across fields as diverse as geographical information science (GISc), corpus linguistics, natural language processing (NLP), human geography, literary studies, and digital humanities. The current state of the art involves using geoparsing to automatically identify the place names in texts and allocate them to a coordinate (Grover et al 2010). Once georeferenced in this way, place names can be read into a geographical information system for mapping and spatial analysis. Analysis can also be conducted using techniques from corpus linguistics and NLP to see what words or themes are associated with the place name such as the place being associated with emotional responses such as being beautiful or inspiring fear. This combination of approaches is known as geographical text analysis (GTA) (Gregory et al 2015). While GTA provides a useful starting point for understanding the geographies within a corpus, it is highly quantitative, is limited to named places for which coordinates can be found, and has little concept of time. Yet, as narratives of journeys make abundantly clear, human experiences of geography are more often subjective and more suited to qualitative representation. In these cases, "geography" is not limited to named places; rather, it incorporates the vague, imprecise, and ambiguous, with references to, for example, "the camp", "the hills in the distance", or "further down the road", and includes the relative locations using terms such as "near to", "on the left", or "a few hours' journey" from. These qualitative representations are necessary contextual referents but cannot be managed within geospatial technologies such as GIS. To understand on a large scale the ways in which humans describe and relate to the world around them, then, we need to be able to visually represent and interpret the geographies authors describe in ways that combine the qualitative nature of described spatial experiences with methods that render them quantitatively analysable.Drawing on a strongly interdisciplinary team, this grant will develop approaches that allow us to identify, extract, visualise, and analyse qualitative and quantitative references to place and time. These methods will be applied to analyses of two large corpora: one a corpus of travel writing about the English Lake District, predominantly written in the 18th and 19th centuries; the other, a corpus of Holocaust survivor testimonies. Although based on very different types of journey - leisure travel and forced migration respectively - both corpora represent a collection of unique voices that coalesce to generate complex cultural and experiential geographies. The project will explore how cutting-edge digital technologies from NLP, corpus linguistics, Qualitative Spatio-Temporal Reasoning (QSTR), GISc, and visual analytics can help us understand how authors themselves represented the geographies that surrounded them and explore the individual and aggregate representation of the sense and experience of place that these texts contain. The resulting applications will have great significance for scholarly and non-academic audiences alike.