Abstract
This chapter describes the integration of a video verification process into newsrooms of TV broadcasters or news agencies, which enables journalists to analyze and assess user-generated videosĀ (UGV) from platforms such as YouTube, Facebook, or Twitter. We regard the organizational integration concerning the workflow, responsibility, and preparations as well as the inclusion of innovative verification tools and services into an existing IT environment. This includes the technical prerequisites required to connect the newsroom to video verification services in the cloud with the combined employment of third-party Web services for retrieval, analysis, or geolocation. We describe the different features to verify source, time, place, content, and rights of the video offered for journalists by theĀ InVID Video Verification Application orVerification App for short, which can serve as a blueprint for realizing a video verification process for professional newsroom systems. In the outlook, we discuss further potential to improve the current verification process through additional services, such as speech-to-text, OCR, translation, or deep fake detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
cf. Chap.Ā 1.
- 6.
- 7.
- 8.
Criteria for newsworthiness are, e.g., timing, significance or proximity, see https://www.mediacollege.com/journalism/news/newsworthy.html.
- 9.
See also: http://verificationhandbook.com/book/chapter8.php, āChapter 8: Preparing for Disaster Coverageā.
- 10.
- 11.
- 12.
- 13.
- 14.
- 15.
- 16.
- 17.
- 18.
- 19.
AFP, for example, dispatches ca. 5000 news stories daily https://www.afp.com/en/agency/about/afp-numbers.
- 20.
The assessment value delivered by a near-duplicate search characterizes the degree of matching between the query video and the compared video.
- 21.
General Data Protection Regulation (GDPR), https://gdpr-info.eu/.
- 22.
- 23.
- 24.
- 25.
- 26.
Lightweight means in this context it is running only on the client and not requiring any server-side or cloud-based installation.
- 27.
- 28.
- 29.
- 30.
- 31.
- 32.
- 33.
- 34.
- 35.
- 36.
Semi-automatic means that the user controls the processing of a tool by selections and inputs.
- 37.
FigureĀ 11.6 āProgress Monitoringā shows an example for processing times of a video.
- 38.
Using a video shown in the US-based The Ellen Show: https://youtu.be/1KFj6b1Xfe8 fabricated from the original: https://youtu.be/ABy_1sLR3s.
- 39.
In order to get acquainted with the Verification App, we recommend to start with a preprocessed video. Examples are (1) The Popes magic trick removing a table cloth: https://www.youtube.com/watch?v=h-AkAF2Tc1k, (2) Paris attacks: https://www.youtube.com/watch?v=4XnGKJAarhA.
- 40.
- 41.
Reference
Thomsen J, Sarioglu A, Fricke R (2016) The linkedtv platform -towards a reactive linked media management system. In: Joint Proceedings of the 4th international workshop on linked media and the 3rd developers Hackshop co-located with the 13th extended semantic web conference ESWC 2016, Heraklion, Crete, Greece, 30 May 2016. http://ceur-ws.org/Vol-1615/limePaper2.pdf
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Fricke, R., Thomsen, J. (2019). Video Verification in the Newsroom. In: Mezaris, V., Nixon, L., Papadopoulos, S., Teyssou, D. (eds) Video Verification in the Fake News Era. Springer, Cham. https://doi.org/10.1007/978-3-030-26752-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-26752-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26751-3
Online ISBN: 978-3-030-26752-0
eBook Packages: Computer ScienceComputer Science (R0)