Conference paper Open Access

Web Video Verification using Contextual Cues

Olga Papadopoulou; Markos Zampoglou; Symeon Papadopoulos; Yiannis Kompatsiaris

As news agencies and the public increasingly rely on User-Generated Content, content verification is vital for news producers and consumers alike. We present a novel approach for verifying Web videos by analyzing their online context. It is based on supervised learning on contextual features: one feature set is based on an existing approach for tweet verification adapted to video comments. The other is based on video metadata, such as the video description, likes/dislikes, and uploader information.
We evaluate both on a dataset of real and fake videos from YouTube, and demonstrate their effectiveness (F-scores: 0.82, 0.79). We then explore their complementarity and show that under an optimal fusion scheme, the classifier would reach an F-score of 0.9. We finally study the performance of the classifier through time, as more comments accumulate, emulating a real-time verification setting.

Files (657.6 kB)
Name Size
657.6 kB Download
Views 242
Downloads 242
Data volume 159.1 MB
Unique views 219
Unique downloads 236


Cite as