Facebook will now ‘fact-check’ photos, videos

Social media site Facebook has announced that they will now include the verification of uploaded photos and videos through its expanded Third Party Fact Checking to rid newsfeeds of false content.

In a post on its newsroom on Thursday (Friday in Manila), Facebook said that they have worked with technology experts to build a “machine learning model” aimed at preventing the spread of misinformation through inaccurately labeled photos and videos.

“To date, most of our fact-checking partners have focused on reviewing articles. However, we have also been actively working to build new technology and partnerships so that we can tackle other forms of misinformation,” Facebook Product Manager Antonia Woodford said.

“Today, we’re expanding fact-checking for photos and videos to all of our 27 partners in 17 countries around the world (and are regularly on-boarding new fact-checking partners). This will help us identify and take action against more types of misinformation, faster,” she added.

Facebook’s partnership with private fact checkers in 17 countries was originally intended for weeding out fake articles and stories.

READ: Facebook partners with fact-checkers to eradicate fake news

With the new technology, photos, especially memes from unverified sources, which are meant to spread sensationalized information, will be filtered.

“We know that people want to see accurate information on Facebook, so for the last two years, we’ve made fighting misinformation a priority. One of the many steps we take to reduce the spread of false news is working with independent, third-party fact-checkers to review and rate the accuracy of content,” Woodford said.

Verifying images

According to Woodford, there are three common categories of misinformation in photos and videos.

“Based on several months of research and testing with a handful of partners since March, we know that misinformation in photos and videos usually falls into three categories: (1) Manipulated or Fabricated, (2) Out of Context, and (3) Text or Audio Claim,” she said.

Woodford also said the machine learning model will study photos and videos and looks for signs, “to identify potentially false content”. These photos will be then forwarded to fact-checkers for review.

“We then send those photos and videos to fact-checkers for their review, or fact-checkers can surface content on their own,” she said.

She added that reviewers will analyze the image’s metadata, which would reveal information about the image or video clip, such as what device was used to capture and upload it, or when and where it was taken.

“Many of our third-party fact-checking partners have expertise evaluating photos and videos and are trained in visual verification techniques, such as reverse image searching and analyzing image metadata, like when and where the photo or video was taken,” she explained.

“Fact-checkers are able to assess the truth or falsity of a photo or video by combining these skills with other journalistic practices, like using research from experts, academics or government agencies,” she added.

Facebook will also be able to identify if original headlines or captions of videos and photos have been manipulated.

“For example, we use optical character recognition (OCR) to extract text from photos and compare that text to headlines from fact-checkers’ articles. We are also working on new ways to detect if a photo or video has been manipulated,” Woodford noted.

“These technologies will help us identify more potentially deceptive photos and videos to send to fact-checkers for manual review,” she said.   /vvp