Abstract
A multi-stage machine-learning architecture assesses the quality of news channels based on substantive media content. A set of recent media items satisfying a news-content criterion is selected from a candidate channel. Multimodal features of the selected media items are processed using a first AI model to generate respective news quality assessments and qualitative information. The news quality assessments are aggregated using weighted metrics to generate aggregated news quality information. The aggregated news quality information and channel-level features are processed using a second AI model to generate a channel-level quality classification. The channel-level quality classification is used to determine whether the candidate channel is included in a corpus of high-quality news sources.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Patwa, Rohit, "Multi-Stage Artificial Intelligence-Based Quality Evaluation of News Channels Using Aggregated Video Analysis", Technical Disclosure Commons, (August 20, 2026)
https://www.tdcommons.org/dpubs_series/11454