ISCRAM Digital Library -- Query Results

Jakob Rogstadius, Claudio Teixeira, Evangelos Karapanos, & Vassilis Kostakos. (2013). An introduction for system developers to volunteer roles in crisis response and recovery. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 874–883). KIT; Baden-Baden: Karlsruher Institut fur Technologie. Abstract: Technological advances, such as software tools for citizen reporting, first responder support, and online collaborative information management and mapping, are enabling new or improved forms of volunteering in humanitarian crisis. However, the change is largely driven by the technical community and many proposed solutions are never integrated into community response efforts, indicating mismatches between designs and real world needs. This paper offers readers with a technical background insight into roles, goals and constraints of humanitarian crisis response. In particular, we present three seemingly conflicting views regarding how citizens can contribute to response activities as spontaneous volunteers. With examples from two field studies and grounded in literature review, we integrate the three viewpoints into a framework explaining how the roles of volunteers and trained professionals shift with increasing severity and scale of a crisis. Based on this framework, we also discuss high-level opportunities for supporting crisis response with new software tools. Keywords: Computer software; Information management; Collaboration; Crisis management; Developer guidelines; Disaster response; System development; Volunteering; Information systems Track: Social Media http://idl.iscram.org/show.php?record=885
Muhammad Imran, Carlos Castillo, Jesse Lucas, Patrick Meier, & Jakob Rogstadius. (2014). Coordinating human and machine intelligence to classify microblog communications in crises. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 712–721). University Park, PA: The Pennsylvania State University. Abstract: An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowd sourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on real world datasets. Keywords: Information systems; Classification accuracy; Disaster response; Human intelligence; Large-scale datum; Machine computations; Machine intelligence; Real-world datasets; Supervised classifiers; Artificial intelligence Track: Social Media in Crisis Response and Management http://idl.iscram.org/show.php?record=612

Abstract: Technological advances, such as software tools for citizen reporting, first responder support, and online collaborative information management and mapping, are enabling new or improved forms of volunteering in humanitarian crisis. However, the change is largely driven by the technical community and many proposed solutions are never integrated into community response efforts, indicating mismatches between designs and real world needs. This paper offers readers with a technical background insight into roles, goals and constraints of humanitarian crisis response. In particular, we present three seemingly conflicting views regarding how citizens can contribute to response activities as spontaneous volunteers. With examples from two field studies and grounded in literature review, we integrate the three viewpoints into a framework explaining how the roles of volunteers and trained professionals shift with increasing severity and scale of a crisis. Based on this framework, we also discuss high-level opportunities for supporting crisis response with new software tools.

Abstract: An emerging paradigm for the processing of data streams involves human and machine computation working together, allowing human intelligence to process large-scale data. We apply this approach to the classification of crisis-related messages in microblog streams. We begin by describing the platform AIDR (Artificial Intelligence for Disaster Response), which collects human annotations over time to create and maintain automatic supervised classifiers for social media messages. Next, we study two significant challenges in its design: (1) identifying which elements must be labeled by humans, and (2) determining when to ask for such annotations to be done. The first challenge is selecting the items to be labeled by crowd sourcing workers to maximize the productivity of their work. The second challenge is to schedule the work in order to reliably maintain high classification accuracy over time. We provide and validate answers to these challenges by extensive experimentation on real world datasets.

Keywords: Information systems; Classification accuracy; Disaster response; Human intelligence; Large-scale datum; Machine computations; Machine intelligence; Real-world datasets; Supervised classifiers; Artificial intelligence

Track: Social Media in Crisis Response and Management

http://idl.iscram.org/show.php?record=612