Bill Hart-Davidson: Don't read the comments

Posted at 8:24 AM, Feb 16, 2017
and last updated 2017-02-16 08:24:25-05

Bill Hart-Davidson is professor of writing, rhetoric and American cultures, a WIDE senior researcher and associate dean for graduate education for the College of Arts and Letters.

“Don’t read the comments!”

That bit of unfortunate advice has become all too common on the internet. It often comes in reaction to the way conversations in comment sections, on social media or in internet forums can stray wildly off topic, veer toward bizarre conspiracy theories or even turn abusive.

The problem can be especially vexing when an outlet trying to host conversations about scientific topics, such as climate change, is overrun by participants aiming to derail the conversation or use the occasion to advocate for or against a particular political cause.

But a project undertaken by the Writing, Information, and Digital Experience research center at MSU aims to help. A team of faculty and students has released a new app, the Faciloscope, developed in conjunction with partners from The Science Museum of Minnesota and the Museum of Life and Science in North Carolina.

The Faciloscope is a tool designed to analyze online conversations like the ones seen on social media or in the comment section of a blog or news story. It was conceived as part of a larger WIDE Research Center project to study online facilitation techniques supported by the Institute for Museum & Library Services.

The app is designed to be especially useful for moderators or facilitators of online conversations, to help them get a global sense of how the conversation is going, and what, if anything, might be done to help move the conversation along in a productive way. It might also help a moderator to know when a conversation has fizzled out or is, perhaps, not worth continuing.

The Faciloscope works by breaking down a conversation into three basic functional “moves” that participants make. It does this by interpreting every sentence-sized chunk of the conversation and classifying the results using a machine-learning algorithm trained to recognize the three moves.

It’s important to note that Faciloscope is not reading and evaluating the truthfulness or accuracy of statements people are making. Rather, it is watching for the kinds of moves people make that affect the overall dynamic of a conversation — moves that can keep it going or shut it down.

We’re proud to have the chance to release the Faciloscope to the primary audience for which it was conceived: informal learning facilitators who are engaging learners in online spaces. And we’re deeply grateful for the guidance of the informal learning experts involved with the original project research.

We also hope that a broad group of online forum moderators who wish to promote discussion and would like a global view of these discussions will find Faciloscope useful. One such group with which we’ve had contact is SpeakUp NC, a group invested in elevating the level of online commentary on hot-button news items.

You can read the comments again!