Geotagged social media posts and volunteered geographic information supply situational observations for public health geomonitoring and decision support systems. Raw records arrive as unstructured text or unevenly distributed coordinate tags. Positional uncertainty and the absence of standardized lineage description limit their direct entry into a geoinformation workflow.
The method formalizes the transformation of social media indicators into a thematic geospatial dataset in the state geodetic reference coordinate system UCS-2000. Input messages are treated as signals typed by spatial role; geocoding proceeds from native coordinates or, through a gazetteer and geospatial artificial intelligence tools, from text alone.
Conversion rules turn a primary signal into a spatial object: the admissible spatial representation follows from the geocoding outcome and the recorded level of spatial uncertainty. Every object carries a uniform mandatory attribute set. The resulting dataset is positioned for compatibility with base geospatial data and serves as an input layer for spatial overlay and subsequent analysis.
Bono, C., Pernici, B., Fernandez-Marquez, J. L., Ravi Shankar, A., Mülâyim, M. O., & Nemni, E. (2022). TriggerCit: Early flood alerting using Twitter and geolocation – a comparison with alternative sources. arXiv. https://arxiv.org/abs/2202.12014 (preprint)
Cabinet of Ministers of Ukraine. (2004). Deiaki pytannia zastosuvannia heodezychnoi referentsnoi systemy koordynat [Some issues of application of the geodetic reference coordinate system] (Resolution No. 1259). https://zakon.rada.gov.ua/laws/show/1259-2004-%D0%BF
DSTU 8774:2018. (2018). Heohrafichna informatsiia. Pravyla modeliuvannia heoprostorovykh danykh [Geographic information. Rules for modelling geospatial data]. DP "UkrNDNTs." (effective from 1 July 2019)
INSPIRE Maintenance and Implementation Group. (2024). D2.8.III.5 Data specification on human health and safety – Technical guidelines (D2.8.III.5_v4.0.0). https://inspire-mif.github.io/technical-guidelines/data/hh/dataspecification_hh.pdf
ISO. (2023). ISO 19157-1:2023. Geographic information – Data quality – Part 1: General requirements. https://www.iso.org/standard/78900.html
Jing, F., Li, Z., Qiao, S., Zhang, J., Olatosi, B., & Li, X. (2023). Using geospatial social media data for infectious disease studies: a systematic review. International Journal of Digital Earth, 16(1), 130–157. https://doi.org/10.1080/17538947.2022.2161652
Karpinskyi, Yu. O., Liashchenko, A. A., Lazorenko, N. Yu., & Kin, D. O. (2023). Osnovy stvorennia interoperabelnykh heoprostorovykh danykh [Fundamentals of building interoperable geospatial data]. Kyiv National University of Construction and Architecture.
Liashchenko, A. A., Karpinskyi, Yu. O., Havryliuk, Ye. Yu., & Cherin, A. H. (2021). Metody ta zasoby zabezpechennia interoperabelnosti komponentiv natsionalnoi infrastruktury heoprostorovykh danykh [Methods and tools for ensuring the interoperability of national spatial data infrastructure components]. Mistobuduvannia ta terytorialne planuvannia, (77), 309–319. https://doi.org/10.32347/2076-815x.2021.77.309-319
Lutsai, K., & Lampert, C. (2024). Predicting the geolocation of tweets using transformer models on customized data. Journal of Spatial Information Science, (29), 69–99. https://doi.org/10.5311/josis.2024.29.295