June 6, 2017 Conference paper Open Access

Olga Papadopoulou; Markos Zampoglou; Symeon Papadopoulos; Yiannis Kompatsiaris

JSON-LD (schema.org) Export

{
  "description": "<p>As news agencies and the public increasingly rely on User-Generated Content, content verification is vital for news producers and consumers alike.\u00a0We 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.<br>\nWe evaluate both on a dataset of real and fake videos from YouTube, and demonstrate their effectiveness (F-scores: 0.82, 0.79).\u00a0We 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.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "CERTH-ITI, Thessaloniki, Greece", 
      "@type": "Person", 
      "name": "Olga Papadopoulou"
    }, 
    {
      "affiliation": "CERTH-ITI, Thessaloniki, Greece", 
      "@type": "Person", 
      "name": "Markos Zampoglou"
    }, 
    {
      "affiliation": "CERTH-ITI, Thessaloniki, Greece", 
      "@type": "Person", 
      "name": "Symeon Papadopoulos"
    }, 
    {
      "affiliation": "CERTH-ITI, Thessaloniki, Greece", 
      "@type": "Person", 
      "name": "Yiannis Kompatsiaris"
    }
  ], 
  "headline": "Web Video Verification using Contextual Cues", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2017-06-06", 
  "url": "https://zenodo.org/record/810474", 
  "@type": "ScholarlyArticle", 
  "keywords": [
    "Video verification", 
    "Context analysis", 
    "Social media", 
    "Fake news"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1145/3078897.3080535", 
  "@id": "https://doi.org/10.1145/3078897.3080535", 
  "workFeatured": {
    "url": "http://mklab.iti.gr/mfsec2017/", 
    "alternateName": "MFSec 2017 @ ICMR2017", 
    "location": "Bucharest, Romania", 
    "@type": "Event", 
    "name": "ACM 2nd International Workshop on Multimedia Forensics and Security, co-located with the 2017 ACM International Conference on Multimedia Retrieval"
  }, 
  "name": "Web Video Verification using Contextual Cues"
}