Home // AIMEDIA 2025, The First International Conference on AI-based Media Innovation // View article

Evaluating AI Editing Algorithms for Video News Reporting

Authors:
Caspian J. Moosburner
Dennis Quandt
Matthias Kowald
Wolfgang Ruppel
Till Dannewald
Matthias Narroschke

Keywords: Artificial Intelligence; AI; video editing; video news; algorithms

Abstract:
With video news gaining more and more popularity, Artificial Intelligence (AI) video editing tools could be implemented to accelerate video news production. A challenging issue, however, is the quality of AI-edited video news and the acceptance of such news by media consumers. A survey with 143 participants is conducted in Germany in order to evaluate the quality of video news clips edited by AI models in comparison to news clips produced by professional human editors. All survey participants are recruited by a commercial survey company. The evaluation of the survey reveals that AI editing is widely undetected by the participants. Overall, the evaluation shows that the quality difference of AI edited video new clips and human edited ones is negligible as confidence intervals of measured quality features overlap. Future research can benefit from investigating the influence of clearly labelled AI content in user evaluations.

Pages: 57 to 61

Copyright: Copyright (c) IARIA, 2025

Publication date: July 6, 2025

Published in: conference

ISBN: 978-1-68558-330-9

Location: Venice, Italy

Dates: from July 6, 2025 to July 10, 2025