Natural language processing for urban research: A systematic review

Abstract

Natural language processing (NLP) has shown potential as a promising tool to exploit under-utilized urban data sources. This paper presents a systematic review of urban studies published in peer-reviewed journals and conference proceedings that adopted NLP. The review suggests that the application of NLP in studying cities is still in its infancy. Current applications fell into five areas: urban governance and management, public health, land use and functional zones, mobility, and urban design. NLP demonstrates the advantages of improving the usability of urban big data sources, expanding study scales, and reducing research costs. On the other hand, to take advantage of NLP, urban researchers face challenges of raising good research questions, overcoming data incompleteness, inaccessibility, and non-representativeness, immature NLP techniques, and computational skill requirements. This review is among the first efforts intended to provide an overview of existing applications and challenges for advancing urban research through the adoption of NLP.

La percepción de espacios públicos en Machala: Caso de estudio Mercado Central

“…Debido al avance en los niveles de conectividad de datos ahora los ciudadanos cuentan con medios alternativos para expresar sus emociones y percepciones (Bardhan, Sunikka-Blank y Haque, 2019; Abali y otros, 2018). La tenencia de perfiles en redes sociales y el uso de contenidos animados cortos están favoreciendo la viralidad en la transmisión de información (Cai, 2021). Se está generando y almacenando una gran cantidad de macrodatos urbanos a una velocidad sin precedentes, siendo esta una forma alternativa para determinar los sentimientos de los ciudadanos y desarrollar investigación científica.…”

“…Jang y Kim (2019) encontraron que los datos de texto recogidos en redes sociales y portales de noticias pueden representar de buena manera la identidad colectiva en un espacio urbano. La ventaja de su uso es que las encuestas suelen ser costosas y demandar mucho tiempo hasta su procesamiento y análisis, por otra parte, los datos almacenados en la internet son más sencillos de obtener y suelen actualizarse con mayor facilidad (Cai, 2021), de manera que no se tiene una incoherencia dinámica de representar a momento presente percepciones pasadas.…”

Do travelers' reviews depend on the destination? An analysis in coastal and urban peer‐to‐peer lodgings

“…Additionally, our study aims to validate advanced natural language processing (NLP) analysis with results attained by traditional methods (cf. Cai, 2021). In this regard, following Sánchez-Franco and Alonso-Dos- Santos (2021Santos ( , p. 2499 approach, our research has to be understood as "a heuristic for theory building, applying an inductive perspective of reasoning to obtain clues that may point researchers and practitioners in a promising direction" (see Figure 1).…”

“…In contrast, NLP offers enormous capabilities of harvesting plenty of enriched UGC. It converts more valuable and credible reviews (created by non-professionals) about personal goals and values to features (or preferences), modeling semantic relationships, and showing relevant topics more efficiently than traditional text analysis (Cai, 2021).…”

Comparative analysis of the government plans of the Peruvian presidential candidates, SDO(UN) and State Policies of the National Agreement based on NLP

“…Natural language processing has shown potential as a promising tool to exploit urban data sources. Authors, such as [Cai, 2021], suggest that the use of urban big data sources is still starting and the most studied areas are: urban governance and management, public health, land use and functional zones, mobility and urban design, having been very useful in expanding study scales and reducing research costs.…”