Fictive motion extraction and classification

Abstract

Fictive motion (e.g. 'The highway runs along the coast') is a pervasive phenomenon in language that can imply both a static and a moving observer. In a corpus of alpine narratives, it is used in three types of spatial descriptions: conveying the actual motion of the observer, describing a vista and communicating encyclopaedic spatial knowledge. This study takes a knowledge-based approach to develop rules for automated extraction and classification of these types based on an annotated corpus of fictive motion instances. In particular, we identify the differences in the set of concepts involved into the production of the three types of descriptions, followed by their linguistic operationalization. Based on that, we build a set of rules that classify fictive motion with an overall precision of 0.87 and recall of 0.71. The article highlights the importance of examining spatially rich, naturally occurring corpora for the lines of work dealing with the automated interpretation of spatial information in texts, as well as, more broadly, investigation of spatial language involved into various types of spatial discourse.

Using textual volunteered geographic information to model nature-based activities: A case study from Aotearoa New Zealand

“…Close reading techniques require a meticulous, iterative approach and are often perceived as time-consuming in the era of big data and machine learning. However, they produce structured, annotated data that can generally be used for training in geographic information retrieval, leading to the systematic extraction and integration of spatial concepts [17]. Distant reading techniques such as topic modeling, on the other hand, obscure structural properties of discourse, do not allow to disambiguate between word senses, and their outputs have less potential for being reused for other purposes.…”

Cogitating on GIS. Response to David O'Sullivan and Matthew Wilson

“…Besides data in the traditional sense, GIS studies embrace dialectics, narratives, semantics, and semiotics (e.g., Brennan‐Horley et al . 2010; Travis, 2014; Egorova et al ., 2018; Curtis et al ., 2019). Bergmann and Lally (2021) advocated for novel geographic imagination systems centering upon space‐producing processes that enfold and entwine space with phenomena.…”

A Review of Geospatial Semantic Information Modeling and Elicitation Approaches

“…Egorova et al [125] developed linguistic rules based on morpho-syntactic patterns for the automated extraction and classification of three types of fictive motion (actual motion of the observer, description of a vista somewhere along the way or encyclopedic knowledge) based on an annotated corpus of alpine narratives.…”