Abstract: Information about location and geographical coordinates in particular, may be very important during a crisis event, especially for search and rescue operations – but currently geo-tagged tweets are extremely rare. Improved capabilities of capturing additional location from Twitter (up to 4 times improvement) are crucial for response efforts given a vast amount of messages exchanged during a crisis event. That is why authors have designed a tool (Text Analysis TWeet lOcator – TAT2) that relies on existing open source text analysis tools with additional services to provide additional hints about people location. Validation process, complementing experimentation and test results, included involvement of end-users (i.e. Public Protection and Disaster Relief services and citizens during a realistic crisis exercise showcase. In addition, the integration of TAT2 with external tools has also been validated.

Abstract: In the last decade, people have increasingly relied on social media platforms such as Twitter to share information on the response to a natural or a man-made disaster. This paper focuses on the aftermath of the Fukushima Daiichi nuclear disaster. Since the disaster, victims and volunteers have been sharing relevant information about radiation measurements by means of social media. The aim of this research is to explore the diffusion of information produced and shared by Twitter bots, to understand the degree of popularity of these sources and to check if these bots deliver original radiation measurements.

Abstract: Recent years have witnessed multiple international protest movements which have purportedly been greatly affected by the use of Twitter, a micro-blogging platform. Social movement actors in Iran, Moldova, Kyrgyzstan and Thailand are thought to have utilized Twitter to spread information, co-ordinate protest activities, evade government censorship and, in some cases, to spread misinformation. We propose a framework for conceptualizing and analyzing Twitter data related to contentious collective action crises. Our primary research goal is to delineate a framework informed with a social movements lens and to demonstrate the framework by means of Twitter usage data related to the Thailand protests of 2010. Our proposed framework concerns itself with two aspects of protest activities and Twitter usage, namely, analyzing the content and structure of messages and our construct of Twitter protest waves.

Abstract: We present Tweet4act, a system to detect and classify crisis-related messages communicated over a microblogging platform. Our system relies on extracting content features from each message. These features and the use of an incident-specific dictionary allow us to determine the period type of an incident that each message belongs to. The period types are: Pre-incident (messages talking about prevention, mitigation, and preparedness), during-incident (messages sent while the incident is taking place), and post-incident (messages related to the response, recovery, and reconstruction). We show that our detection method can effectively identify incident-related messages with high precision and recall, and that our incident-period classification method outperforms standard machine learning classification methods.

Abstract: The most popular micro blogging platform Twitter has been the topic of a variety of research papers related to disaster and crisis management. As an essential first step and basis for a real-time methodology to exploit Twitter for event detection, localization and ultimately semantic content analysis, a functional model to describe the amount of tweets during a day has been developed. It was derived from a corpus of messages in an exemplary area of investigation. To satisfy the different daily behavior on particular days, two types of days are distinguished in this paper. Moreover, keyword-adjusted data is used to point out the potential of semantic tweet analysis in following steps. The consideration of spatial event descriptions in relevant tweets could significantly improve and accelerate the perception of a disaster. The results from the conducted tests demonstrate the capability of the functional model to detect events with significant social impact in Twitter data.

Abstract: Event detection from social media is a challenging task due to the volume, the velocity and the variety of user-generated data requiring real-time processing. Despite recent works on this subject, a generalized and scalable approach that could be applied across languages and topics has not been consolidated, yet. In this paper, we propose a methodology for real-time event detection from Twitter data that allows users to select a topic of interest by defining a simple set of keywords and a matching rule. We implement the proposed methodology and evaluate it with real data to detect different types of events.

Abstract: Social media have proven to be useful resources for spreading verified information during natural disasters. Nevertheless, little attention has hitherto been devoted to the peculiarities of constructing effective tweets (and tweet formats), or to common users’ comprehension of tweets conveying scientific information. In this paper, social scientists and seismologists collaborated in order to elaborate and test a standardized tweet structure to be used during earthquakes, expanding on the results of a quali-quantitative research project. The tweet format is specifically designed to launch an innovative information service by Istituto Nazionale di Geofisica e Vulcanologia (INGV): tweeting the automatic detection of earthquakes with a magnitude greater than 3. This paper illustrates the steps of the research process that led to elaborating a tweet format that will be used in the next few months by the official Twitter account @INGVterremoti.

Abstract: Semi-structured interviews were conducted with U.S. public sector emergency managers to probe barriers to use of social media and reactions to possible software enhancements to support such use. The three most frequently described barriers were lack of personnel time to work on use of social media, lack of policies and guidelines for its use, and concern about the trustworthiness of pulled data. The most popular of the possible technological enhancements described for Twitter are filtering by category of user/contributor, and display of posts on a GIS system with a map-based display.

Abstract: Many machine learning techniques have been proposed to reduce the information overload in social media data during an emergency situation. Among such techniques, domain adaptation approaches present greater potential as compared to supervised algorithms because they don’t require labeled data from the current disaster for training. However, the use of domain adaptation approaches in practice is sporadic at best. One reason is that domain adaptation algorithms have parameters that need to be tuned using labeled data from the target disaster, which is presumably not available. To address this limitation, we perform a study on one domain adaptation approach with the goal of understanding how much source data is needed to obtain good performance in a practical situation, and what parameter values of the approach give overall good performance. The results of our study provide useful insights into the practical application of domain adaptation algorithms in real crisis situations.

Abstract: Several research studies have shown the importance of social media data for humanitarian aid. Among others, the issue of missing and lost people during disasters and emergencies is crucial for disaster managers. This work analyzes Twitter data from a recent wildfire event to determine its usefulness for the mitigation of the missing and found people issue. Data analysis performed using various filtering techniques, and trend analysis revealed that Twitter contains important information potentially useful for emergency managers and volunteers to tackle this issue. Many tweets were found containing full names, partial names, location information, and other vital clues which could be useful for finding missing people.

Abstract: We present the first release of EMTerms (Emergency Management Terms), the largest crisis-related terminological resource to date, containing over 7,000 terms used in Twitter to describe various crises. This resource can be used by practitioners to search for relevant messages in Twitter during crises, and by computer scientists to develop new automatic methods for crises in Twitter.
The terms have been collected from a seed set of terms manually annotated by a linguist and an emergency manager from tweets broadcast during 4 crisis events. A Conditional Random Fields (CRF) method was then applied to tweets from 35 crisis events, in order to expand the set of terms while overcoming the difficulty of getting more emergency managers’ annotations.
The terms are classified into 23 information-specific categories, by using a combination of expert annotations and crowdsourcing. This article presents the detailed terminology extraction methodology, as well as final results.

Abstract: Social media enables fast information exchange and status reporting during crises. Filtering is usually required to identify the small fraction of social media stream data related to events. Since deep learning has recently shown to be a reliable approach for filtering and analyzing Twitter messages, a Convolutional Neural Network is examined for filtering crisis-related tweets in this work. The goal is to understand how to obtain accurate and robust filtering models and how model accuracies tend to behave in case of new events. In contrast to other works, the application to real data streams is also investigated. Motivated by the observation that machine learning model accuracies highly depend on the used data, a new comprehensive and balanced compilation of existing data sets is proposed. Experimental results with this data set provide valuable insights. Preliminary results from filtering a data stream recorded during hurricane Florence in September 2018 confirm our results.

Abstract: Crisis situations require specific information to organize and respond to the events. The need of information is important and emergency management cells aim at gathering them as much as possible to build a common operational picture (COP) of the field. Also, citizens are using more and more social media to share what is happening around them during exceptional events. Social media, such as Twitter, Facebook or Instagram therefore participate in the exchange of information related to the crisis. Consequently, it is important to be able to take advantage of this by integrating citizens' social media data into the decision-making process. Up to this day, many tools exist in the literature. However, information systems integrating social media data into the COP are rarely used in the facts because they are still resource-consuming. This leads to a paradoxical situation where decision-makers are looking for information to organize their resources while victims and witnesses’ willing to share information is not taken into account by rescue organizations. In this context, some possible necessary improvements are identified. Among them, “how the added-value information extracted thanks to such social media-oriented system should be integrated in the decision-making process?” echoes to this context. Consequently, how to fully integrate the information provided by social media data, in times of crisis, to improve the common understanding and thus the collaborative response of the responders.