Abstract: In this research-in-progress paper, the role of social media during the two months of the Iranian post-election crisis in Summer 2009 has been studied. In search of emergent social phenomena, particular emphasis is given to online participation and collaboration throughout social network sites. This study demonstrates the extent to which such media can gain prominence and challenge traditional practices as well as challenging the next level of research and development of social media during crisis situations.

Abstract: This paper offers a descriptive account of Twitter (a micro-blogging service) across four high profile, mass convergence events-two emergency and two national security. We statistically examine how Twitter is being used surrounding these events, and compare and contrast how that behavior is different from more general Twitter use. Our findings suggest that Twitter messages sent during these types of events contain more displays of information broadcasting and brokerage, and we observe that general Twitter use seems to have evolved over time to offer more of an information-sharing purpose. We also provide preliminary evidence that Twitter users who join during and in apparent relation to a mass convergence or emergency event are more likely to become long-term adopters of the technology.

Abstract: In this paper, we propose a low-tech solution for use by microbloggers that could enhance their ability to rapidly produce parsable, crisis-relevant information in mass emergencies. We build upon existing research on the use of social media during mass emergencies and disasters. Our proposed intervention aims to leverage the affordances of mobile microblogging and the drive to support citizen reporting within current behavioral Twitter-based microblogging practice. We introduce a prescriptive, tweet-based syntax that could increase the utility of information generated during emergencies by gently reshaping current behavioral practice. This offering is grounded in an understanding of current trends in norm evolution of Twitter use, an evolution that has progressed quickly but appears to be stabilizing around specific textual conventions.

Abstract: Online Social Networking Sites (SNS) are becoming extremely popular and can be employed in a variety of contexts. They permit the establishment of global relationships that are domain related or can be based on some general need shared by the participants. Emergency domain related websites, each with their own stated mission, are becoming widespread. Can a social network offer a solution to bringing emergency domain-related entities together as a 'one stop shop?' We propose to investigate whether the social network paradigm can be used to enable individuals and organizations to collaborate in mutually beneficial ways, in all stages of emergency management: mitigation, preparedness, response and recovery. Emergency management students were surveyed to examine the concept of social networks and their acceptance as a potential tool. The results of this exploratory research show overwhelming agreement that SNS should be considered a viable solution to the problems plaguing information dissemination and communications in the emergency domain.

Abstract: The purpose of this paper was to identify an effective user-requirements data analysis method for informing the design of a Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) management decision support system. Data were collected from a large simulation involving medical, police, hazmat/firefighters and subjected to three different kinds of analysis methods: Social Network Analysis, Content Analysis, and Observational Analysis. While all three methods yielded valuable information, the observational method was by far the best for the present purpose.

Abstract: We developed an intelligent information visualization tool to enable public health officials to detect healthrelated trends in any geographic area of interest, based on Twitter data. Monitoring emergent events such as natural disasters, disease outbreaks, and terrorism is vital for protecting public health. Our goal is to support situation awareness (SA) for personnel responsible for early detection and response to public health threats. To achieve this goal, our application identifies the most frequently tweeted illnesses in a ranked chart and map for a selected geographic area. Automated processes mine and filter health-related tweets, visualize changes in rankings over time, and present other keywords frequently associated with each illness. User-centered visualization techniques of monitoring, inspecting, exploring, comparing and forecasting supports all the three stages of SA. An evaluation conducted with experts in health-related domains provided significant insights about awareness of localized health trends and their practical use in their daily work.

Abstract: “Participatory Sensing is an approach to data collection and interpretation in which individuals, acting alone or in groups, use their personal mobile devices and web services to systematically explore interesting aspects of their worlds ranging from health to culture.”[ http://www.mobilizingcs.org/about/participatory-sensing] Data from the physical world of sensors and the virtual world of social networks and Linked Data can be combined into interesting high-level information. Sensor data can assist in localized information retrieval by giving the search engine direct access to events happening locally in the real world. Participatory sensing enables individuals and communities to collect and share granular, accurate data about a particular area. This paper describes work in progress within the FP7 EU-funded project SMART project to develop a multimedia search engine over content and information streaming from both the physical world and the Internet. We will identify some ethical problems regarding the use and storage of such data.

Abstract: In this paper we tell a version of the story of the bombing of the Boston Marathon. At first, two online groups gathered images, video and textual information concerning the bombing of the Boston Marathon and shared these with the FBI and amongst themselves. Secondly, these groups then created mechanisms to conduct their own investigation into the identities of the perpetrators. Finally, the larger national media followed the results of these online group investigations and reported these as fact to a national audience. We choose Twitter as our data repository and conducted quantitative analyses of tweets sent during the Boston Bombing. The implications for not incorporating public crowd participation within the standard operating procedures of emergency services may result in either a loss of public confidence in the slow-moving nature of official response to uncontrollable, dangerous and irresponsible public and media participation that exacerbates the negative effects of any disaster.

Abstract: In an increasingly networked society citizens at disaster sites utilize information and communication technology (ICT) to communicate needs or to share information. In order to understand better emergent possibilities and implications of applying ICT for supporting public participation in disasters, we surveyed 57 respondents regarding several key user aspects as perceived usefulness, socially related issues, or deployment. Surprisingly, our results show a clear tendency to use a disaster specific application instead of using everyday services as facebook or Twitter. However, such application poses the risk to loose its focus fading slowly away after once downloading it. Further study is needed to understand if these results are representative regarding public society. © 2012 ISCRAM.

Abstract: Social media tools are seeing use in crisis situations. Authorities have recognized the value of such tools and are beginning to use services such as Facebook and Twitter to disseminate official information. However, the use of the social media concept as an internal, operational tool by emergency services is in its early stages. Current social media tools for mobile devices are of potential value, yet security concerns can render such systems unsuitable for operational use, and the user interface can hinder operational efficiency due to the inheritance of a text based model for input and display. The research to be described is examining interaction methods that may improve the efficiency and usability of mobile device-based social media for operational use by police services. A Twitter like model for police activity reports can provide a means for enhanced situational awareness for police command authorities, and for individual officers or patrol units engaged in the “professional” media interchanges. The proposed model, SUMO, is based on a hybrid symbolic and text interface to rapidly enter status, integrated with geolocation, and sensor-based data to automatically capture key information, and thereby minimizing the amount effort required create a complete status update.

Abstract: In this paper, we introduce Tweedr, a Twitter-mining tool that extracts actionable information for disaster relief workers during natural disasters. The Tweedr pipeline consists of three main parts: classification, clustering and extraction. In the classification phase, we use a variety of classification methods (sLDA, SVM, and logistic regression) to identify tweets reporting damage or casualties. In the clustering phase, we use filters to merge tweets that are similar to one another; and finally, in the extraction phase, we extract tokens and phrases that report specific information about different classes of infrastructure damage, damage types, and casualties. We empirically validate our approach with tweets collected from 12 different crises in the United States since 2006.

Abstract: Microblogging services like Twitter afford opportunities for real time determination of situation awareness during crises as people report, via their statuses, information about events on the ground. An important component of the information included in a tweet are mentions of place names that may be sites of damage, injuries, or relief efforts. Methods for extracting these place names and determining the actual location being referenced are an essential part of the suite of tools required for automated extraction of situation awareness from tweets. Extracting and disambiguating place name mentions from text have been areas of extensive research. Twitter, however, presents challenges given the 140 character restriction on status and the informal, abbreviated language that are a norm in this communication channel. Named entity recognizers, which are dependent on labeled training data, may not be useful in this medium for extracting location mentions because the typical training domains for these taggers are absent the noise found in Twitter statuses. Additionally, the contextual information that is necessary for disambiguating place names is not always present. In this paper, we demonstrate a new technique, RapidGeo, for extracting and disambiguating place names from a location specific Twitter feed using an unsupervised technique for tagging location mentions and relying on the known geographic context of the feed for disambiguation. Our location tagging technique performs much better than an off-the-shelf named entity recognizer and we achieve reasonable precision in disambiguating extracted place names. We argue that such fast, high precision, unsupervised approaches are needed when important, actionable information is required from noisy data sources such as Twitter. © 2012 ISCRAM.