Veracity and velocity of social media content during
breaking news: analysis of November 2015 Paris shootings
Veracity and velocity of social media content during
breaking news: analysis of November 2015 Paris shootings
Social media sources are becoming increasingly important in journalism. Under breaking news deadlines semi-automated support for identification and verification of content is critical. We describe a large scale content-level analysis of over 6 million Twitter, You Tube and Instagram records covering the first 6 hours of the November 2015 Paris shootings. We ground our analysis by tracing how 5 ground truth images used in actual news reports went viral. We look at velocity of newsworthy content and its veracity with regards trusted source attribution. We also examine temporal segmentation combined with statistical frequency counters to identify likely eyewitness content for input to real-time breaking content feeds. Our results suggest attribution to trusted sources might be a good indicator of content veracity, and that temporal segmentation coupled with frequency statistical metrics could be used to highlight in real-time eyewitness content if applied with some additional text filters.
Association for Computing Machinery
Middleton, Stuart
404b62ba-d77e-476b-9775-32645b04473f
12 April 2016
Middleton, Stuart
404b62ba-d77e-476b-9775-32645b04473f
Wiegand, Stefanie and Middleton, Stuart
(2016)
Veracity and velocity of social media content during
breaking news: analysis of November 2015 Paris shootings.
In WWW '16 Companion: Proceedings of the 25th International Conference Companion on World Wide Web.
Association for Computing Machinery..
(doi:10.1145/2872518.2890095).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Social media sources are becoming increasingly important in journalism. Under breaking news deadlines semi-automated support for identification and verification of content is critical. We describe a large scale content-level analysis of over 6 million Twitter, You Tube and Instagram records covering the first 6 hours of the November 2015 Paris shootings. We ground our analysis by tracing how 5 ground truth images used in actual news reports went viral. We look at velocity of newsworthy content and its veracity with regards trusted source attribution. We also examine temporal segmentation combined with statistical frequency counters to identify likely eyewitness content for input to real-time breaking content feeds. Our results suggest attribution to trusted sources might be a good indicator of content veracity, and that temporal segmentation coupled with frequency statistical metrics could be used to highlight in real-time eyewitness content if applied with some additional text filters.
Text
390962.pdf
- Accepted Manuscript
More information
Accepted/In Press date: 15 December 2015
e-pub ahead of print date: 11 April 2016
Published date: 12 April 2016
Additional Information:
Paper given at SNOW 2016: Third Workshop on Social News on the Web, part of the 25th World Wide Web Conference.
Venue - Dates:
SNOW Workshop at WWW 2016 Conference, Montreal, Canada, 2016-04-12 - 2016-04-12
Organisations:
IT Innovation
Identifiers
Local EPrints ID: 390962
URI: http://eprints.soton.ac.uk/id/eprint/390962
PURE UUID: 8f903a93-8e45-430e-9c98-2a9b0752f829
Catalogue record
Date deposited: 19 Apr 2016 11:07
Last modified: 16 Mar 2024 03:18
Export record
Altmetrics
Contributors
Author:
Stefanie Wiegand
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
