Natural Language Processing to the Rescue? Extracting "Situational Awareness" Tweets During Mass Emergency

By Sudha Verma, Sarah Vieweg, William J. Corvey, Leysia Palen, James H. Martin, Martha Palmer, Aaron Schram, K. Anderson. International Conference on Web and Social Media, 2011

384 citations recorded by the source corpus.

In times of mass emergency, vast amounts of data are generated via computer-mediated communication (CMC) that are difficult to manually cull and organize into a coherent picture. Yet valuable information is broadcast, and can provide useful insight into time- and safety-critical situations if captured and analyzed properly and rapidly. We describe an approach for automatically identifying messages communicated via Twitter that contribute to situational awareness, and explain why it is beneficial for those seeking information during mass emergencies.We collected Twitter messages from four different crisis events of varying nature and magnitude and built a classifier to automatically detect messages that may contribute to situational awareness, utilizing a combination of hand-annotated and automatically-extracted linguistic features. Our system was able to achieve over 80% accuracy on categorizing tweets that contribute to situational awareness. Additionally, we show that a classifier developed for a specific emergency event performs well on similar events. The results are promising, and have the potential to aid the general public in culling and analyzing information communicated during times of mass emergency.

Subfields: Artificial Intelligence, Communication, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/c62de088af618ab1a5057f0d4a52161acab0d8e0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Communication

In Sociology and Political Science

Citations in the corpus

Undesirable biases in NLP: Averting a crisis of measurement (2022, background): “…2013), conversations with customer services, help desks and emergency services are automatically transcribed and analyzed to improve service (e.g., Verma et al., 2011), millions of medical and legal texts are automatically searched to find relevant passages, at times supporting decisions that may…”
The limits of crisis data: analytical and ethical challenges of using social and mobile data to understand disasters (2015, background): “Other reports said that individual text messages provided valuable tactical information (Palen et al. 2010; Verma et al. 2011).”
TweetCred: Real-Time Credibility Assessment of Content on Twitter (2014, background): “ content. They developed an automated framework to enhance situational awareness during emergency situations, extracting location and location-referencing information from users’ tweets. Verma et al. [20] used natural language processing techniques to build an automated classier to detect messages o”
Robust Text Classification in the Presence of Confounding Bias (2016, background): “…et al. 2009) and computational epidemiology (Marathe and Ramakrish-nan 2013) have created new demand for text classiﬁcation in areas such as public health surveillance (Dredze 2012), political science (Dahll¨of 2012), crisis response (Verma et al. 2011), and marketing (Chamlertwat et al. 2012).”
Conference on Empirical Methods in Natural Language Processing Proceedings of the Fourth International Workshop on Natural Language Processing for Social Media Socialnlp@emnlp2016 Chairs' Welcome Identifying and Categorizing Disaster-related Tweets Why Do They Leave: Modeling Participation in Online (background): “Closely related to this work is that of Verma et al. (2011), who constructed classifiers to identify tweets that demonstrate situational awareness in four datasets (Red River floods of 2009 and 2010, the Haiti earthquake of 2010, and Oklahoma fires of 2009).”
Faking Sandy: characterizing and identifying fake images on Twitter during Hurricane Sandy (2013, methodology): “used natural language techniques to build an automated classifier to detect messages on Twitter that may contribute to situational awareness [25].”
Socializing in emergencies - A review of the use of social media in emergency situations (2015, background): “…simultaneously, including civilians, government or private organizations, journalists, news sites and others that create an information overload during emergencies, making it difficult to find, organize, understand and act upon it (Hagar, 2013; Verma et al., 2011; Kavanaugh et al., 2011).”
NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets (2013, background): “, 2009), health (Chew and Eysenbach, 2010; Salathé and Khandelwal, 2011), and disaster management (Verma et al., 2011; Mandel et al., 2012).”
Major life changes and behavioral markers in social media: case of childbirth (2013, background): “Language has been shown to provide useful psychological markers [29], and prior research [36,38] has shown that usage of language has the potential to convey information about individuals’ behavior, their social surroundings, contexts and crises they are in.”
A Framework and Tool for Collaborative Extraction of Reliable Information (2013, background): “For example, it has been noted that it may be possible to automatically identify information that contributes to situational awareness in general (Verma et al., 2011), or for more pinpoint tasks such as identifying information about safety of evacuees (Neubig et al., 2011), evacuation routes…”