Function-Based Search of Place Using Theoretical, Empirical and Probabilistic Patterns

Abstract

Searching for places rather than traditional keyword-based search represents significant challenges. The most prevalent method of addressing place-related queries is based on place names but has limited potential due to the vagueness of natural language and its tendency to lead to ambiguous interpretations. In previous work we proposed a system-oriented logic-based formalization of place that goes beyond place names by introducing composition patterns of place which enable function-based search of space. In this study, we introduce flexibility into these patterns in terms of what is included when describing the spatial composition of a place using two distinct approaches, based on modal and probabilistic logic. Additionally, we propose a novel automated process of extracting these patterns relying on both theoretical and empirical knowledge, using statistical and spatial analysis and statistical relational learning. The proposed methodology is exemplified through the use case of locating all areas within London that support shopping-related functionality. Results show that the newly introduced patterns can identify more relevant areas, additionally offering a more fine-grained representation of the level of support of the required functionality.

Operationalizing places in GIScience: A review

“…We also found studies that operationalized places with generalized examples that were not attached to existing cities or regions, such as restaurants (Jordan et al., 1998) and airports (Papadakis, Baryannis, & Blaschke, 2018). In the works of Papadakis, Resch, and Blaschke (2016), Papadakis, Petutschnig, and Blaschke (2018), Papadakis, Baryannis, Petutschnig, and Blaschke (2019), Papadakis, Resch, and Blaschke (2020), shopping areas were the places utilized as the object of study for their function‐based model, which was first published in 2016 and has been substantially developed over the years. Finally, two articles carried out studies on unusual places: dream settings and “shithole” (sic).…”

“…The model category integrates the works that focused on building, designing, and implementing operational models of places within GIS environments. The objectives of these papers varied from designing prototypical to fully operational models within GIS, either using or not using real‐world examples based on their proposed frameworks (e.g., ElGindy & Abdelmoty, 2014; Jordan et al., 1998; Papadakis et al., 2019). As for the formalization category, it includes the papers whose main stated objectives concerned formally describing place and related concepts through different methods for further integration and operationalization in geographic information systems and spatial analysis (e.g., Blaschke & Piralilou, 2018; Scheider & Janowicz, 2014).…”

Combining Design Patterns and Topic Modeling to Discover Regions That Support Particular Functionality

“…For instance, knowledge (either raw or encoded in a pattern) can be used to adapt the LDA process itself, e.g., by rescaling the document-word frequency matrix, as is done using check-in data. Alternatively, VGI data can be used to adjust knowledge-based patterns, an approach similar in spirit to the empirical and probabilistic patterns proposed in [34].…”

Putting Geographical Information Science in Place – Towards Theories of Platial Information and Platial Information Systems

“…Besides affordances and activities, the functions of places have been examined. Papadakis et al (2020, 2019, 2018b, 2016) and Wang et al (2018) have, for instance, related places to nearby Points of Interests (POIs) to infer which functions a place could serve for. Such way of thinking about activities, affordances, and functions reminds of work by Schatzki (‘site ontology’; 2003).…”

“…Most prominently, place names have acted as references to places for long, and these have been examined widely in Geographical Information Science by Jones et al (2008), McKenzie et al (2018), Vasardani et al (2013), Chen et al (2019), Goodchild and Hill (2008), and Maué (2013). Besides pure reference, the way places can be described by natural language has been investigated by Adams and McKenzie (2013), Papadakis et al (2019), Edwardes and Purves (2007), and Hobel et al (2016). Social Media is a special form of a text medium.…”