Geo‐text data and data‐driven geospatial semantics

Abstract

Many datasets nowadays contain links between geographic locations and natural language texts. These links can be geotags, such as geotagged tweets or geotagged Wikipedia pages, in which location coordinates are explicitly attached to texts. These links can also be place mentions, such as those in news articles, travel blogs, or historical archives, in which texts are implicitly connected to the mentioned places. This kind of data is referred to as geo-text data. The availability of large amounts of geo-text data brings both challenges and opportunities. On the one hand, it is challenging to automatically process this kind of data due to the unstructured texts and the complex spatial footprints of some places. On the other hand, geo-text data offers unique research opportunities through the rich information contained in texts and the special links between texts and geography. As a result, geo-text data facilitates various studies especially those in data-driven geospatial semantics. This paper discusses geo-text data and related concepts. With a focus on data-driven research, this paper systematically reviews a large number of studies that have discovered multiple types of knowledge from geo-text data. Based on the literature review, a generalized workflow is extracted and key challenges for future work are discussed.

How urban places are visited by social groups? Evidence from matrix factorization on mobile phone data

“…Do their movements frequently interact with each other in space and time? At an aggregate level, studies suggest that human activity space is in good agreement with the socioeconomic divisions in cities (Xu, Belyi, Bojic, & Ratti, 2017, 2018. At an individual level, it has been revealed that a large portion of the places visited by an individual usually locate within the social circles centered at his/her nearest social tie locations (Wang, Kang, Bettencourt, Liu, & Andris, 2015;Yuan & Raubal, 2016).…”

“…For instance, social media data that contain a large volume of texts and images are becoming a major descriptive indicator of people's cognition and emotional feelings attached to urban place in terms of sign-in, re-emergence, repetition, and aggregation (Jenkins, Croitoru, Crooks, & Stefanidis, 2016;Wu, Wang, Shi, Gao, & Liu, 2019). Machine learning and data mining methods have become mainstream tools for extracting thematic topics from textual data to quantify human activities and emotions at specific places (Gao et al, 2017;Hu, 2018;Tran, Shin, & Choi, 2018). Popular approaches include the Word2Vec model and its geo-enhanced variants (Yan, Janowicz, Mai, & Gao, 2017;Zhai et al, 2019).…”

“…They are manifestations of the semantics of the individual POIs, as well as the semantics of the corresponding urban place where those POIs locate inside. Based on sophisticated natural language processing (NLP) analyses, the sense of urban place can be meaningfully quantified in terms of morphology, functionality, and sentiment (Hu, 2018). The derived semantics of urban places serve as good indicators of place identity for distinguishing social groups' social, economic, and environmental preferences in the process of conducting daily desired activities.…”

A Review of Geospatial Semantic Information Modeling and Elicitation Approaches

“…Data-driven geospatial semantics refers to a bottom-up approach for eliciting geospatial knowledge from natural language texts that contain either explicit or implicit locations of places [99]. It is distinct from top-down or expert-driven approaches that extract geospatial knowledge from experts in a specific field.…”

GTMapLens: Interactive Lens for Geo‐Text Data Browsing on Map

“…Geo‐text data [Hu18] contains texts and themes linked to geolocations. Examples include geo‐tagged social media, real estate information, community events, crime reports, consumer reviews, and so on.…”