The Coral Project Builds a Tool to Tackle Comments

Headed by Andrew Losowsky, the Coral Project which began work in May of 2015, is described in the project’s launch news as a collaborative partnership between The New York Times, The Washington Post and the Knight Foundation; all existing under the umbrella of Mozilla.

‘The Coral Project has been created to change how news publishers and audiences interact. Right now, most sites struggle with finding meaningful engagement and controlling abuse. We’re going to build open source tools to empower both readers and publishers to reshape the conversation. That means changing the dreaded comments box, and also so much more — it might mean user-generated content, forums, on-site identities, and some things that have yet to be built. It will also mean changing how some editors and reporters think about their work. ‘

This first project attempts to address the problems around readers comments, by giving publishers a tool which will analyse collected data from submitted comments, in order to build profiles which distinguish the good commenters from the bad. Greg Barber (director of digital news projects at The Washington Post), describes the project in a new post on the Coral website;

‘The product will gather a mix of existing data points from readers of comments and other user contributions, such as likes, shares, and flags, and pair it with new data, such as ratings of commenters from users and editors, reporters, and community managers. The result will be a system that manages the reputations of users, allowing publishers to stratify their users by levels of trust’.

The project is looking for partners to road test the tool which is so new it doesn’t currently have a name. Joseph Lichterman of Nieman Lab (also funded by the Knight Foundation) describes how privacy issues are being considered;

The Coral Project won’t host any of the data, and the tool will comply with each publication’s privacy policies, Losowsky said. The data the Coral Project collects will be anonymized logs of behaviors, like how many times users have replied to comments. The project may also do semantic analysis of the comments. Ultimately, though, Losowsky said the Coral Project’s goal is to make the tool flexible enough for each outlet to use on its own terms. “In conversation with the publishers, we’ll get a sense of what different metrics will make sense for these different ideas of trust and reputation and then give the publishers the tools to shift those metrics in ways that make sense for them and get analytics out of that,” he said.

Also of primary importance to the success of the project (as Lichterman points out), will be a consideration of the feelings of the community of readers which attaches itself to a publication. Whilst many feel that the trolls must be controlled if comments sections are to maintain a healthy ecosystem, it remains to be seen how a balance between moderation and censorship can be happily maintained.