Can we predict a riot? Disruptive event detection using Twitter
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96289898
- Type
- D - Journal article
- DOI
-
10.1145/2996183
- Title of journal
- ACM Transactions on Internet Technology
- Article number
- 18
- First page
- -
- Volume
- 17
- Issue
- 2
- ISSN
- 1533-5399
- Open access status
- Not compliant
- Month of publication
- March
- Year of publication
- 2017
- URL
-
http://dx.doi.org/10.1145/2996183
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
C - Cybersecurity, privacy and human centred computing
- Citation count
- 25
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- An event detection framework fusing novel classification and clustering methods to detect “disruptive events”. Evaluated on a large-scale real-world dataset of tweets during the August 2011 riots in England, we show that our system can perform as well as terrestrial sources, and even better in some cases. The HM Inspectorate of Constabulary timeline of the riots was used to verify that our method detected events on Twitter prior to police receiving 999 calls. Altmetric data reports widespread media coverage of the work included United Press International, Times of India, and New Scientist (https://www.altmetric.com/details/18380709/news?src=bookmarklet).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -