Researchers:
Motti Zohar, Lea Wittenberg, (Department of Geography and Environmental Studies, University of Haifa); Avigdor Gal (Faculty of Industrial Engineering & Management, Technion), Efrat Morin (Institute of Earth Sciences, Hebrew University of Jerusalem) and Ran Nof, (the Geological Survey of Israel).
Abstract:
During the last decade, the social network of Twitter has become a robust platform for distributing messages (tweets) among numerous subscribers worldwide. To date, Twitter is used by more than 300 million users worldwide. In Israel the growth of twitter subscribers is by ~100,000 since 2014 and to date consists of over 1,000,000 subscribers. The tweets, up to 280 characters only, can be sent via web pages, mobile devices or third-party Twitter applications. During and around the occurrence of natural hazards, people tend to over-tweet and consequently, the number of tweets raise significantly. While Twitter is already in use for near real-time alerts, processes for extracting reported damage from tweets and examining the resulted spatial distribution are still under development. In the proposed study it is suggested to acquire tweets made prior to and after natural hazards such as floods, fire and earthquakes that occurred in Israel and its close surroundings. It is planned to temporally and spatially analyze the fetched tweets in order to (1) achieve near real-time alerts; (2) analyze damage patterns and affected regions; (3) validate initial damage estimations and calibrate reference scenarios used for preparing the initial damage estimations and (4) inspect how this data can assist in management of cascading events during the first hours after a catastrophe occurs.
See publications:
Zohar, M., Gennosar, B., Avny, R., Tessler, N., & Gal, A. (2023). Spatiotemporal analysis in high resolution of tweets associated with the November 2016 wildfire in Haifa (Israel). International Journal of Disaster Risk Reduction, 103720. https://doi.org/10.1016/j.ijdrr.2023.103720
https://www.sciencedirect.com/
Zohar, M. (2021). Geolocating tweets via spatial inspection of information inferred from tweet meta-fields. International Journal of Applied Earth Observation and Geoinformation, 105, 102593. https://doi.org/10.1016/j.jag.2021.102593