Economic Control of Quality of Manufactured Product.

Social media platforms provide active communication channels during mass convergence and emergency events such as disasters caused by natural hazards. As a result, first responders, decision makers, and the public can use this information to gain insight into the situation as it unfolds. In particular, many social media messages communicated during emergencies convey timely, actionable information. Processing social media messages to obtain such information, however, involves solving multiple challenges including: parsing brief and informal messages, handling information overload, and prioritizing different types of information found in messages. These challenges can be mapped to classical information processing operations such as filtering, classifying, ranking, aggregating, extracting, and summarizing. We survey the state of the art regarding computational methods to process social media messages and highlight both their contributions and shortcomings. In addition, we examine their particularities, and methodically examine a series of key subproblems ranging from the detection of events to the creation of actionable and useful summaries. Research thus far has, to a large extent, produced methods to extract situational awareness information from social media. In this survey, we cover these various approaches, and highlight their benefits and shortcomings. We conclude with research challenges that go beyond situational awareness, and begin to look at supporting decision making and coordinating emergency-response actions.

/pdf/processing-social-media-messages-in-mass-emergency-a-survey-2wkyj3y36n.pdf

Processing Social Media Messages in Mass Emergency: A Survey

Understanding human mobility is crucial for a broad range of applications from disease prediction to communication networks. Most efforts on studying human mobility have so far used private and low resolution data, such as call data records. Here, we propose Twitter as a proxy for human mobility, as it relies on publicly available data and provides high resolution positioning when users opt to geotag their tweets with their current location. We analyse a Twitter dataset with more than six million geotagged tweets posted in Australia, and we demonstrate that Twitter can be a reliable source for studying human mobility patterns. Our analysis shows that geotagged tweets can capture rich features of human mobility, such as the diversity of movement orbits among individuals and of movements within and between cities. We also find that short- and long-distance movers both spend most of their time in large metropolitan areas, in contrast with intermediate-distance movers’ movements, reflecting the impact of different modes of travel. Our study provides solid evidence that Twitter can indeed be a useful proxy for tracking and predicting human movement.

/pdf/understanding-human-mobility-from-twitter-1i2hx4cyi7.pdf

Understanding Human Mobility from Twitter

Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i.e., items of information that are unverified at the time of posting. At the same time, the openness of social media platforms provides opportunities to study how users share and discuss rumours, and to explore how to automatically assess their veracity, using natural language processing and data mining techniques. In this article, we introduce and discuss two types of rumours that circulate on social media: long-standing rumours that circulate for long periods of time, and newly emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages. We provide an overview of research into social media rumours with the ultimate goal of developing a rumour classification system that consists of four components: rumour detection, rumour tracking, rumour stance classification, and rumour veracity classification. We delve into the approaches presented in the scientific literature for the development of each of these four components. We summarise the efforts and achievements so far toward the development of rumour classification systems and conclude with suggestions for avenues for future research in social media mining for the detection and resolution of rumours.

/pdf/detection-and-resolution-of-rumours-in-social-media-a-survey-4wwcvcnn3i.pdf

Detection and Resolution of Rumours in Social Media: A Survey

Could social media data aid in disaster response and damage assessment? Countries face both an increasing frequency and an increasing intensity of natural disasters resulting from climate change. During such events, citizens turn to social media platforms for disaster-related communication and information. Social media improves situational awareness, facilitates dissemination of emergency information, enables early warning systems, and helps coordinate relief efforts. In addition, the spatiotemporal distribution of disaster-related messages helps with the real-time monitoring and assessment of the disaster itself. We present a multiscale analysis of Twitter activity before, during, and after Hurricane Sandy. We examine the online response of 50 metropolitan areas of the United States and find a strong relationship between proximity to Sandy's path and hurricane-related social media activity. We show that real and perceived threats, together with physical disaster effects, are directly observable through the intensity and composition of Twitter's message stream. We demonstrate that per-capita Twitter activity strongly correlates with the per-capita economic damage inflicted by the hurricane. We verify our findings for a wide range of disasters and suggest that massive online social networks can be used for rapid assessment of damage caused by a large-scale disaster.

/pdf/rapid-assessment-of-disaster-damage-using-social-media-336uh6nd9k.pdf

Rapid assessment of disaster damage using social media activity.

There have been recent efforts to use social media to estimate demographic characteristics, such as age, gender or income, but there has been little work on investigating the effect of data acquisition methods on producing these estimates. In this paper, we compare four different Twitter data acquisition methods and explore their effects on the prediction of one particular demographic characteristic: occupation (or profession). We present a comparative analysis of the four data acquisition methods in the context of estimating occupation statistics for Australia. Our results show that the social network-based data collection method seems to perform the best. However, we note that each different data collection approach has its own benefits and limitations.

The Effects of Data Collection Methods in Twitter

The Emergency Situation Awareness (ESA) tool provides crowd-sourced information in near-real-time from Twitter about all-hazard events for emergency managers. ESA currently collects tweets from Australia and New Zealand and processes them to identify unexpected incidents, to monitor ongoing emergency events and provides access to an archive to explore past events. It is operated using a map based interactive web site and has processed over 2 billion tweets since September 2011. ESA has been developed by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) and has been trialed by numerous emergency services organisations throughout Australia. Tweets are processed as a data stream using text mining techniques and natural language processing tools to identify content relevant to emergency managers. ESA is deployed as a distributed information architecture consisting of a combination of commodity open source technologies, such as an Apache Solr index, a relational database, messaging infrastructure, web servers and supporting software toolkits, as well as purpose built components for message burst detection, event identification and notification, message classification and clustering, geo-coding and searching. In this chapter, an overview of ESA is presented showing how tweets are gathered and processed. Three case studies are outlined explaining how ESA is used to detect earthquakes, monitor bushfire events and as a general all-hazard monitoring tool in a crisis coordination centre. We also note some of the issues we have encountered from using our tool and present an overview of our research road map noting the planned extensions and new features.

Using Crowd Sourced Content to Help Manage Emergency Events

Linking hydrologic models and data: the OpenMI approach

The opportunity for improved decision making has been enhanced in recent years through the public availability of a wide variety of information. In Australia, government data is routinely made available and maintained in the http://data.gov.au repository. This is a single point of reference for data that can be reused for purposes beyond that originally considered by the data custodians. Similarly a wealth of citizen information is available from the Australian Bureau of Statistics. Combining this data allows informed decisions to be made through planning scenarios.

/pdf/scenario-planning-case-studies-using-open-government-data-21mf064ux8.pdf

Scenario Planning Case Studies Using Open Government Data

The CSIRO ICT Centre’s Information Engineering Laboratory has been involved in a number of emergency management related projects over the last four years. In these projects we have applied our software engineering expertise in the areas of web technologies, user interfaces and databases along with research capability in machine learning, distributed systems, text processing and data stream management. This process has increased our understanding of the various roles and responsibilities of different government departments at the federal and state level and of the wider emergency services community. The research agenda of the CSIRO is broad and its application to the area of disaster management is no different. In this field of research, one of the CSIRO’s aims is to improve the process and service delivery of disaster management in Australia and to provide high-impact solutions to strengthen the disaster resilience of the nation in the future. As well as the projects reviewed in this paper, there are other research activities underway or completed within the CSIRO that address the issues of disaster management, see Hawkins et al. (2012) for an overview. The focus of this paper is to present three recent CSIRO projects related to emergency management, highlighting their differences and similarities with a focus on the challenges encountered and a categorisation of the target data items utilised. The Pilot Impacts Portal, http://www.fend.org.au/, is a web accessible user interface to a collection of national data items describing historical fire emergency and natural disaster events and their associated impacts. The project was a collaboration with Fire & Rescue NSW that aimed to better understand the economic, social and environmental impacts on communities due to disaster events. The Emergency Response Intelligence Capability project, http://eric.csiro.au/, is a collaboration with the Australian Government Department of Human Services Emergency Management team who are responsible for intelligence gathering and situation reporting during emergency events. The CSIRO have developed a tool that supports the department’s operational tasks by automatically gathering data from a range of sources, presenting the data on a map based website and generating customised situation reports. The Emergency Situation Awareness system, https://esa.csiro.au/, analyses Twitter messages to provide early detection of emergency events. It extracts situation awareness information as the disaster unfolds, effectively crowd sourcing relevant details and providing time critical information that allows emergency services to respond rapidly and appropriately. A short overview of each project is presented. Each system makes use of different types of information: historical archives, community details, near-real-time authoritative event information and social media content. Combining all of this information will provide emergency management organisations with better quality information for decision making resulting in improved community outcomes. Social media is a new channel of information that can provide further intelligence about emergency events. Authoritative information is being published on Twitter by the emergency services community which can be augmented with non-authoritative crowd sourced social media content to provide a better understanding of emergency events.

Bella Robinson

Papers

The Effects of Data Collection Methods in Twitter

Using Crowd Sourced Content to Help Manage Emergency Events

Linking hydrologic models and data: the OpenMI approach

Scenario Planning Case Studies Using Open Government Data

Information Integration for Emergency Management:recent CSIRO case studies