Can twitter save lives? A broad-scale study on visual social media analytics for public safety

Dennis Thom, Robert Krüger, Thomas Ertl

    Research output: Contribution to journalArticlepeer-review

    Abstract

    The use of social media monitoring for public safety is on the brink of commercialization and practical adoption. To close the gap between research and application, this paper presents results of a two-phase study on visual analytics of social media for public safety. For the first phase, we conducted a large field study, in which 29 practitioners from disaster response and critical infrastructure management were asked to investigate crisis intelligence tasks based on Twitter data recorded during the 2013 German Flood. To this end, the ScatterBlogs visual analytics system, a platform that provides reference implementations of tools and techniques popular in research, was given to them as an integrated toolbox. We reviewed the domain experts' individual performances with the system as well as their comments about the usefulness of techniques. In the second phase, we built on this feedback about ScatterBlogs in order to sketch out a system and create additional tools specifically adapted to the collected requirements. The performance of the old lab prototype is finally compared against the re-design in a controlled user study.

    Original languageEnglish (US)
    Article number7364284
    Pages (from-to)1816-1829
    Number of pages14
    JournalIEEE Transactions on Visualization and Computer Graphics
    Volume22
    Issue number7
    DOIs
    StatePublished - Jul 1 2016

    Keywords

    • Evaluation
    • Geographic Visualization
    • Social Media
    • Twitter
    • User Study
    • Visual Analytics

    ASJC Scopus subject areas

    • Software
    • Signal Processing
    • Computer Vision and Pattern Recognition
    • Computer Graphics and Computer-Aided Design

    Fingerprint

    Dive into the research topics of 'Can twitter save lives? A broad-scale study on visual social media analytics for public safety'. Together they form a unique fingerprint.

    Cite this