Agile is the Association of Geographic Information Laboratories in Europe. The 28th annual conference took place from 10th to 13th June 2025 at Dresden University of Technology, Germany. The theme was “Geographic Information Science responding to Global Challenges”.

Lex presented the following papers:

##1

Comber, A., Asher, M., Wang, Y., Kieu, M., Bui, Q.T., Nguyen, T.T.H., Phe, H.H. and Malleson, N., 2025. Characterising neighbourhood dynamics through social media anlaysis and house sales transactions. AGILE: GIScience Series, 6, p.18.

Abstract: This paper describes a two stage approach for identify neighbourhood areas that may undergoing gentrification related changes. It summarises classic hedonic house price data over time (2014-2023) for each neighbourhood, and compares neighbourhood average price with those of local nearby areas. This enables neighbourhoods experience high relative increases in price to be identified as potentially gentrifying areas. Social media data for these areas were extracted and analysed using a large language model and used to score individual social media posts with the a measure of the degree to which their content indicates that the neighbourhood is experiencing change, providing confirmatory evidence or not of gentrification. A number of areas of further work are identified.

The full conference paper is available here

##2

Comber, A., Harris, P., and Brunsdon, C. (2025). How much time to include in multiscale space-time regressions? Optimising predictor variable temporal lags, AGILE GIScience Ser., 6, 19, https://doi.org/10.5194/agile-giss-6-19-2025

Abstract: Generalised Additive Models (GAMs) with Gaussian process bases have been proposed as a framework for constructing spatially varying coefficient (SVC) and spatially and temporally varying coefficient (STVC) regression models, that overcome many of the theoretical problems and technical limitations associated with geographically weighted approaches. Recent work has considered the SVC case in detail and this is being extended to the temporal case. However, while spatial lags and dependencies are well handled by many existing methods, one of the critical issues in space-time modelling is how to determine appropriate temporal lags for individual predictor variables that may exhibit different temporal dependencies with the target variable. This paper demonstrates an outline approach for optimising these. Additionally, lags determined in this way may be used to inform on the temporal margins used to parameterise space-time tensor products smooths in GAM based STVC approaches.

The full conference paper is available here