Predicting civil unrest by categorizing Dutch twitter events

  • Rik van Noord*
  • , Florian A. Kunneman
  • , Antal van den Bosch
  • *Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    2 Citations (Scopus)
    325 Downloads (Pure)

    Abstract

    We propose a system that assigns topical labels to automatically detected events in the Twitter stream. The automatic detection and labeling of events in social media streams is challenging due to the large number and variety of messages that are posted. The early detection of future social events, specifically those associated with civil unrest, has a wide applicability in areas such as security, e-governance, and journalism. We used machine learning algorithms and encoded the social media data using a wide range of features. Experiments show a high-precision (but low-recall) performance in the first step. We designed a second step that exploits classification probabilities, boosting the recall of our category of interest, social action events.

    Original languageEnglish
    Title of host publicationBNAIC 2016 Benelux Conference on Artificial Intelligence
    Subtitle of host publicationProceedings of the twenty-eight Benelux Conference on Artificial Intelligence
    EditorsBert Bredeweg, Tibor Bosse
    Place of PublicationAmsterdam
    PublisherSpringer
    Pages3-16
    Number of pages14
    Edition28
    ISBN (Electronic)978-3-319-67468-1
    ISBN (Print)978-3-319-67467-4
    DOIs
    Publication statusPublished - 15-Sept-2017
    Event28th Benelux Conference on Artificial Intelligence, BNAIC 2016 - Amsterdam, Netherlands
    Duration: 10-Nov-201611-Nov-2016

    Publication series

    NameCommunications in Computer and Information Science
    Volume765
    ISSN (Print)1865-0929

    Conference

    Conference28th Benelux Conference on Artificial Intelligence, BNAIC 2016
    Country/TerritoryNetherlands
    CityAmsterdam
    Period10/11/201611/11/2016

    Keywords

    • Civil unrest
    • Event categorization
    • Event detection

    Fingerprint

    Dive into the research topics of 'Predicting civil unrest by categorizing Dutch twitter events'. Together they form a unique fingerprint.

    Cite this