User-generated content -commonly referred to as "eyewitness media"- has become an essential component in journalism and news reporting. Increasingly more news providers, such as news agencies, broadcasters and Web-only players have set up teams of dedicated investigators or are in the process of training parts of their journalistic workforce to gather and evaluate material from social networks and the Web. If verified, such content can be invaluable in delivering a news story. However, while source checking and verification is as old as journalism itself, the verification of digital material is a relatively young field, with protocols and assisting tools still being developed. In this work, we present our efforts towards a Web-based image verification platform. The platform, currently in its alpha stage, features image tampering detection using a number of state-of-the-art algorithms and image metadata visualization. We discuss the current strengths and limitations of the platform and the implemented state-of-the-art with respect to the specific requirements of the task, resulting from its Web-based nature and its intended use by news investigators with limited expertise in the domain of image forensics.
As User Generated Content takes up an increasing share of the total Internet multimedia traffic, it becomes increasingly important to protect users (be they consumers or professionals, such as journalists) from potentially traumatizing content that is accessible on the web. In this demonstration, we present a web service that can identify disturbing or graphic content in images. The service can be used by platforms for filtering or to warn users prior to exposing them to such content. We evaluate the performance of the service and propose solutions towards extending the training dataset and thus further improving the performance of the service, while minimizing emotional distress to human annotators.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.