Ross S Purves

Understanding the role of humans in environmental change is one of the most pressing challenges of the 21st century. Environmental narratives - written texts with a focus on the environment - offer rich material capturing relationships between people and surroundings. We take advantage of two key opportunities for their computational analysis: massive growth in the availability of digitised contemporary and historical sources, and parallel advances in the computational analysis of natural language. We open by introducing interdisciplinary research questions related to the environment and amenable to analysis through written sources. The reader is then introduced to potential collections of narratives including newspapers, travel diaries, policy documents, scientific proposals and even fiction. We demonstrate the application of a range of approaches to analysing natural language computationally, introducing key ideas through worked examples, and providing access to the sources analysed and accompanying code. The second part of the book is centred around case studies, each applying computational analysis to some aspect of environmental narrative. Themes include the use of language to describe narratives about glaciers, urban gentrification, diversity and writing about nature and ways in which locations are conceptualised and described in nature writing. We close by reviewing the approaches taken, and presenting an interdisciplinary research agenda for future work. The book is designed to be of interest to newcomers to the field and experienced researchers, and set out in a way that it can be used as an accompanying text for graduate level courses in, for example, geography, environmental history or the digital humanities.

Significant amounts of information available today contain references to places on earth. Traditionally such information has been held as structured data and was the concern of Geographic Information Systems (GIS). However, increasing amounts of data in the form of unstructured text are available for indexing and retrieval that also contain spatial references. This monograph describes the field of Geographic Information Retrieval (GIR) that seeks to develop spatially-aware search systems and support user's geographical information needs. Important concepts with respect to storing, querying and analysing geographical information in computers are introduced, before user needs and interaction in the context of GIR are explored. The task of associating documents with coordinates, prior to their indexing and ranking forms the core of any GIR system, and different approaches and their implications are discussed. Evaluating the resulting systems and their components, and different paradigms for doing so continue to be an important area of research in GIR and are illustrated through several examples. The monograph provides an overview of the research field, and in so doing identifies key remaining research challenges in GIR.