Multilingual Analysis of Twitter News in Support of Mass Emergency Events

Abstract

Social media are increasingly becoming a source for event-based early warning systems in the sense that they can help to detect natural disasters and support crisis management during or after disasters. In this article the authors study the problems of analyzing multilingual twitter feeds for emergency events. Specifically, they consider tsunami and earthquakes as one possible originating cause of tsunami. Twitter messages provide testified information and help to obtain a better picture of the actual situation. Generally, local civil protection authorities and the population are likely to respond in their native language. Therefore, the present work focuses on English as “lingua franca” and on under-resourced Mediterranean languages in endangered zones, particularly Turkey, Greece, and Romania. The authors investigated ten earthquake events and defined four language-specific classifiers that can be used to detect earthquakes by filtering out irrelevant messages that do not relate to the event. The final goal is to extend this work to more Mediterranean languages and to classify and extract relevant information from tweets, translating the main keywords into English. Preliminary results indicate that such a filter has the potential to confirm forecast parameters of tsunami affecting coastal areas where no tide gauges exist and could be integrated into seismographic sensor networks.

Is a Pretrained Model the Answer to Situational Awareness Detection on Social Media?

“…In addition, it is not uncommon to mix a few languages and use localized lingo on social media to form a unique language to express emotion, especially in a multicultural environment (Zielinski & Bügel, 2012). This approach is evident as compared with a formal language (e.g., English), the localized vernacular language can better resonate with the community (Asiaone, 2015).…”

Mining Twitter Data for Landslide Events Reported Worldwide

“…A multiservice composition approach was applied to the detection of landslides . Multilingual reporting of earthquakes and tsunami was analyzed using Twitter (Bügel & Zielinski, 2013). The focus of the system lies in improving the coverage of realtime landslide detection based on multilingual citizen sensing reported in multiple languages.…”

Microblogging during the European Floods 2013

“…Support Vector Machines (SVM) are superior to naïve Bayesian multinomial (Yang et al, 2013). Bügel and Zielinski (2013) studied the challenges of multilingual twitter feed analysis. In particular they investigated ten earthquakes and defined four language-specific classifiers.…”