Extracting geographical information from a large corpus of social media text is useful for monitoring live events such as natural disasters and public health crises. However, the noisy nature of texts creates challenges for reliable geoparsing, geocoding, and geotagging. These challenges can be remedied with relation extraction (RE) to efficiently identify geographic relations, but existing RE solutions are not domain-specific for geographic contexts. In this study, we domain-adapt and validate existing RE models to identify variations of geographic relations used in unstructured texts. We analyze 163,037 tweets containing counties and state names of the United States with 1,672 annotated tweets as training data. We apply five RE models with domain-adaptation: (1) our own heuristics-based model; (2) OpenIE; (3) BERT; (4) GPT-3.5-turbo; and (5) Mistral. We identify a list of lexically similar but semantically different relations and categorized them into meronymic, prepositional, ‘include’, ‘locate’, geographic noun, and other spatial relations. The contributions of this study are twofold: (1) we provide a list of geographic relations that can be used for GIS tasks that require more accurate detection of location from text; (2) we show that the performance of large language models (LLMs) improved with domain-specific training for geographic relation extraction.

This study investigates the impact of five relation types towards taxonomy alignment problems and finds that the presence and prevalence of each relation type have profound impact on the resulting merged solutions. The five relation types used in this study are: equal , include , included-in , overlap , and disjoint . We take a logic-based approach to work with the taxonomy alignment problem, and evaluate (1) the presence of a relation type and (2) the prevalence of a relation type towards the number of possible worlds (merged solutions) produced. We find that equal relation type has a minimal effect on the number of possible worlds, whereas include , included-in , overlap , and disjoint are all significantly impacting the number of possible worlds. We also find that more than one of a relation type from either of the four ( include , included-in , overlap , disjoint ) can substantially increase the number of possible worlds, with overlap and disjoint contributing to a profound exponential growth of that number. This study demonstrates how choices of relation types are important in taxonomy alignment problems, and that aligning taxonomies beyond equivalence is necessary to accurately capture the nuances of real-world taxonomies. • This study is the first to examine different relation types on taxonomy alignments. • This study finds that only using equals for mapping is not enough. • This study demonstrates how combinations of relation types on alignment matters.

The Ukraine-Russia conflict has brought sizable detrimental impact to the global energy, food, finance, and manufacturing industries, as well to many affected people. In this paper, we use Twitter (now X) to automatically identify who needs what from text data and how the types of needs that we categorized and standardize evolved throughout this conflict. Our findings suggest that the Ukraine expresses a need for weapons, Russia for land, Europe for gas, and America for leadership. The majority of needs expressed on Twitter during this conflict are related to the categories transportation, military, health & medical, financial and money, energy, and essential items (food, water, shelter, non-food items). Stated needs changed as the conflict escalated or fell into stalemate. Needs also varied depending on the tweet's location, with tweets from Ukraine's neighboring countries being related to food and medicine, while tweets from non-neighboring countries stated needs for clothing and tents. Tweets written in Ukrainian and Russian shared similar need terms, such as medicines and kits, compared to English tweets, which expressed needs such as ammunition and humanitarian aid. Our comparison of needs across four different disaster events, namely this conflict, an earthquake, a major hurricane, and the COVID-19 pandemic, showed how needs differ depending on the nature of the crisis and how domain-adjustment of needs categories is necessary. We contribute to the crisis informatics literature by (1) validating a methodology for using tweets to study the demand and supply of things that different stakeholders need during crisis events and (2) testing, comparing, and improving the fit of widely used need classification schemas for studying crisis from different domains.

Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, Jana Diesner. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.