Identification of Fine-Grained Location Mentions in Crisis Tweets

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 7164–7173 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 7164 Identification of Fine-Grained Location Mentions in Crisis Tweets Sarthak Khanal, Maria Traskowsky, Doina Caragea Kansas State University Manhattan, KS 66506 {sarthakk, mariatraskowsky, dcaragea}@ksu.edu Abstract Identification of fine-grained location mentions in crisis tweets is central in transforming situational awareness information extracted from social media into actionable information. Most prior works have focused on identifying generic locations, without considering their specific types. To facilitate progress on the fine-grained location identification task, we assemble two English tweet crisis datasets and manually annotate them with specific location types. The first dataset contains tweets from a mixed set of crisis events, while the second dataset contains tweets from the global COVID-19 pandemic. We investigate the performance of state-of-the-art deep learning models for sequence tagging on these datasets, in both in-domain and cross-domain settings. Keywords: Crisis management, Social-media, Location identification, Deep-Learning 1. Introduction We have witnessed a large number of crisis situations in recent years, from natural disasters to man-made disas- ters and also to deadly animal and human health crises, culminating with the ongoing COVID-19 public health crisis. Affected individuals often turn to social media (e.g., Twitter or Facebook) to report useful informa- tion, or ask for help (Sakaki et al., 2010; Vieweg et al., 2010; King, 2018). Information contributed on so- cial media by people on the ground can be invaluable to emergency response organizations in terms of gain- ing situational awareness, prioritizing resources to best assist the affected population, addressing concerns, and even saving lives (King, 2018). Many recent studies have focused on identifying in- formative tweets posted by individuals affected by a crisis, and classifying those tweets according to situ- ational awareness categories useful for crisis response and management (Imran et al., 2015). However, for sit- uational awareness information extracted from social media to be actionable, knowing the corresponding ge- ographic location is of key importance. For example, location information enables responders to perform fast assessment of the damage produced by a natural disas- ter (Villegas et al., 2018), or to respond to requests for help coming from affected individuals or institutions (e.g., hospitals or schools). In the case of COVID-19 health crisis, location information can also be used to identify trends by locations (e.g., stance of a commu- nity towards various health recommendations) (Mutlu et al., 2020; Miao et al., 2020), and subsequently em- ploy that information to prevent dissemination of mis- information and rumors, and resurgence of the novel coronavirus. Unfortunately, only a very small percentage of tweets are geotagged (Mahmud et al., 2012). Furthermore, even when geolocation information is available, that lo- cation may not be the location mentioned in the tweet text (Ikawa et al., 2013). According to Vieweg et al. (2010), the location in the tweet text is usually the lo- cation needed for monitoring and/or responding to an emergency. Table 1 shows several examples of tweets posted during …

Content truncated to 500 words